/
398 of 398 variablesANTHROPIC_API_KEY
ANTHROPIC_*
API key sent as
X-Api-Key header. When set, this key is used instead of your Claude Pro, Max, Ultra, Team, or Enterprise subscription even if you are logged in. In non-interactive mode (-p), the key is always used when present. In interactive mode, you are prompted to approve the key once before it overrides your subscription. To use your subscription instead, run unset ANTHROPIC_API_KEYANTHROPIC_AUTH_TOKEN
ANTHROPIC_*
Custom value for the
Authorization header (the value you set here will be prefixed with Bearer )ANTHROPIC_AWS_API_KEY
ANTHROPIC_*
Workspace API key for Claude Platform on AWS, generated in the AWS Console. Sent as
x-api-key and takes precedence over AWS SigV4ANTHROPIC_AWS_BASE_URL
ANTHROPIC_*
Override the Claude Platform on AWS endpoint URL. Use for custom regions or when routing through an LLM gateway. Defaults to
https://aws-external-anthropic.{region}.api.aws. Claude Code resolves the region with the same precedence as on Amazon BedrockANTHROPIC_AWS_WORKSPACE_ID
ANTHROPIC_*
Required for Claude Platform on AWS. Sent on every request as the
anthropic-workspace-id headerANTHROPIC_BASE_URL
ANTHROPIC_*
Override the API endpoint to route requests through a proxy or gateway. For what happens when that gateway rejects MCP tool search, see Tool search through an LLM gateway. As of v2.1.196, Remote Control is disabled when this points at a host other than
api.anthropic.com, matching its behavior on Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft FoundryANTHROPIC_BEDROCK_BASE_URL
ANTHROPIC_*
Override the Amazon Bedrock endpoint URL. Use for custom Amazon Bedrock endpoints or when routing through an LLM gateway. See Amazon Bedrock
ANTHROPIC_BEDROCK_MANTLE_BASE_URL
ANTHROPIC_*
Override the Amazon Bedrock Mantle endpoint URL. See Mantle endpoint
ANTHROPIC_BEDROCK_REGION_PREFIX
ANTHROPIC_*
Cross-region inference profile prefix (
us, eu, apac, jp, au, or global) Claude Code tries first instead of the one derived from the AWS region. Ignored in AWS GovCloud regions. Requires Claude Code v2.1.224 or later. See Amazon BedrockANTHROPIC_BEDROCK_SERVICE_TIER
ANTHROPIC_*
Amazon Bedrock service tier (
default, flex, or priority). Sent as the X-Amzn-Bedrock-Service-Tier header. See Amazon BedrockANTHROPIC_BETAS
ANTHROPIC_*
Comma-separated list of additional
anthropic-beta header values to include in API requests. Claude Code already sends the beta headers it needs; use this to opt into an Anthropic API beta before Claude Code adds native support. Unlike the --betas flag, which requires API key authentication, this variable works with all auth methods including Claude.ai subscriptionANTHROPIC_CUSTOM_HEADERS
ANTHROPIC_*
Custom headers to add to requests (
Name: Value format, newline-separated for multiple headers). If a name or value contains a character an HTTP header can't carry, such as a curly quote or a zero-width space, the request fails with an error that identifies the pair by position. Requires Claude Code v2.1.227 or later. Invalid request header value lists the exact character set and where the check runs. A value that sets a credential, org or tenant, routing, or API-behavior header, such as Authorization or Host, counts as a setting that needs approval when server-managed settings deliver it. From project or local settings, such a value follows the rules for when env values applyANTHROPIC_CUSTOM_MODEL_OPTION
ANTHROPIC_*
Model ID to add as a custom entry in the
/model picker. Use this to make a non-standard or gateway-specific model selectable without replacing built-in aliases. See Model configurationANTHROPIC_CUSTOM_MODEL_OPTION_DESCRIPTION
ANTHROPIC_*
Display description for the custom model entry in the
/model picker. Defaults to Custom model (<model-id>) when not setANTHROPIC_CUSTOM_MODEL_OPTION_NAME
ANTHROPIC_*
Display name for the custom model entry in the
/model picker. When not set, the entry shows the model's name if Claude Code recognizes the ID, and the model ID otherwiseComma-separated list of capabilities the custom model supports, for example
effort,thinking. See Model configurationANTHROPIC_DEFAULT_FABLE_MODEL
ANTHROPIC_*
Model ID that the
fable alias resolves to, and the ID Claude Code recognizes as a Fable model for automatic model fallback on third-party providers. See Model configurationANTHROPIC_DEFAULT_FABLE_MODEL_DESCRIPTION
ANTHROPIC_*
Display description for the pinned Fable model in the
/model picker. When not set, the row shows a default description that begins Custom Fable model. See Model configurationANTHROPIC_DEFAULT_FABLE_MODEL_NAME
ANTHROPIC_*
Display name for the pinned Fable model in the
/model picker. When not set, the row shows the model's name if Claude Code recognizes the pinned ID, and the pinned ID otherwise. See Model configurationComma-separated list of capabilities the pinned Fable model supports, for example
effort,thinking. See Model configurationANTHROPIC_DEFAULT_HAIKU_MODEL
ANTHROPIC_*
Model ID that the
haiku alias resolves to, also used for background functionality. See Model configurationANTHROPIC_DEFAULT_HAIKU_MODEL_DESCRIPTION
ANTHROPIC_*
Display description for the pinned Haiku model in the
/model picker. When not set, the row shows a default description that begins Custom Haiku model. See Model configurationANTHROPIC_DEFAULT_HAIKU_MODEL_NAME
ANTHROPIC_*
Display name for the pinned Haiku model in the
/model picker. When not set, the row shows the model's name if Claude Code recognizes the pinned ID, and the pinned ID otherwise. See Model configurationComma-separated list of capabilities the pinned Haiku model supports, for example
effort,thinking. See Model configurationANTHROPIC_DEFAULT_MODEL
ANTHROPIC_*
Model that new sessions start on by default. Requires Claude Code v2.1.236 or later. See Set a default model for new sessions
ANTHROPIC_DEFAULT_OPUS_MODEL
ANTHROPIC_*
Model ID that the
opus alias resolves to, and that opusplan uses while Plan Mode is active. See Model configurationANTHROPIC_DEFAULT_OPUS_MODEL_DESCRIPTION
ANTHROPIC_*
Display description for the pinned Opus model in the
/model picker. When not set, the row shows a default description that begins Custom Opus model. See Model configurationANTHROPIC_DEFAULT_OPUS_MODEL_NAME
ANTHROPIC_*
Display name for the pinned Opus model in the
/model picker. When not set, the row shows the model's name if Claude Code recognizes the pinned ID, and the pinned ID otherwise. See Model configurationComma-separated list of capabilities the pinned Opus model supports, for example
effort,thinking. See Model configurationANTHROPIC_DEFAULT_SONNET_MODEL
ANTHROPIC_*
Model ID that the
sonnet alias resolves to, and that opusplan uses when Plan Mode is not active. See Model configurationANTHROPIC_DEFAULT_SONNET_MODEL_DESCRIPTION
ANTHROPIC_*
Display description for the pinned Sonnet model in the
/model picker. When not set, the row shows a default description that begins Custom Sonnet model. See Model configurationANTHROPIC_DEFAULT_SONNET_MODEL_NAME
ANTHROPIC_*
Display name for the pinned Sonnet model in the
/model picker. When not set, the row shows the model's name if Claude Code recognizes the pinned ID, and the pinned ID otherwise. See Model configurationComma-separated list of capabilities the pinned Sonnet model supports, for example
effort,thinking. See Model configurationANTHROPIC_FEDERATION_RULE_ID
ANTHROPIC_*
Federation rule ID for Workload Identity Federation. When you set it together with
ANTHROPIC_ORGANIZATION_ID, Claude Code selects federation credentials, which rank above your /login credential. See authentication precedenceANTHROPIC_FOUNDRY_API_KEY
ANTHROPIC_*
API key for Microsoft Foundry authentication (see Microsoft Foundry)
ANTHROPIC_FOUNDRY_AUTH_TOKEN
ANTHROPIC_*
Bearer token for Microsoft Foundry authentication, such as a Microsoft Entra access token. Claude Code sends it as the
Authorization: Bearer header. Takes precedence over ANTHROPIC_FOUNDRY_API_KEY and over the Azure default credential chain. See Microsoft Foundry. Requires Claude Code v2.1.203 or laterANTHROPIC_FOUNDRY_BASE_URL
ANTHROPIC_*
Full base URL for the Microsoft Foundry resource (for example,
https://my-resource.services.ai.azure.com/anthropic). Alternative to ANTHROPIC_FOUNDRY_RESOURCE (see Microsoft Foundry)ANTHROPIC_FOUNDRY_RESOURCE
ANTHROPIC_*
Microsoft Foundry resource name (for example,
my-resource). Claude Code refuses a URL or host name. Required if ANTHROPIC_FOUNDRY_BASE_URL is not set (see Microsoft Foundry)ANTHROPIC_MODEL
ANTHROPIC_*
Name of the model setting to use (see Model Configuration)
ANTHROPIC_ORGANIZATION_ID
ANTHROPIC_*
Organization ID for Workload Identity Federation. Set it together with
ANTHROPIC_FEDERATION_RULE_ID. See authentication precedenceANTHROPIC_PROFILE
ANTHROPIC_*
Name of the Anthropic profile to authenticate with, such as one created by
ant auth login or by signing in to a Console account without an API key. See authentication precedenceANTHROPIC_SMALL_FAST_MODEL
ANTHROPIC_*
\[DEPRECATED] Name of Haiku-class model for background tasks
ANTHROPIC_SMALL_FAST_MODEL_AWS_REGION
ANTHROPIC_*
Override AWS region for the Haiku-class model when using Amazon Bedrock or Amazon Bedrock Mantle. On Amazon Bedrock, this only takes effect when
ANTHROPIC_DEFAULT_HAIKU_MODEL or the deprecated ANTHROPIC_SMALL_FAST_MODEL is also set, since Amazon Bedrock otherwise runs background tasks on the default Sonnet model or the primary model in the session regionANTHROPIC_VERTEX_BASE_URL
ANTHROPIC_*
Override Google Cloud's Agent Platform endpoint URL. Use for custom Google Cloud's Agent Platform endpoints or when routing through an LLM gateway. See Google Cloud's Agent Platform
ANTHROPIC_VERTEX_PROJECT_ID
ANTHROPIC_*
GCP project ID that Google Cloud's Agent Platform requests are addressed to. See Configure GCP credentials
ANTHROPIC_WORKSPACE_ID
ANTHROPIC_*
Workspace ID for workload identity federation. Set this when your federation rule is scoped to more than one workspace so the token exchange knows which workspace to target
Override the 5-minute body idle timeout that aborts a streaming model response when no bytes arrive. Set to
0 to turn the timeout off, for example when a slow gateway or local model pauses longer than 5 minutes between chunks, or 1 to keep it on for every provider. When unset, the timeout is active on providers other than the direct Anthropic API, Claude Platform on AWS, and Amazon Bedrock with CLAUDE_ENABLE_BYTE_WATCHDOG_BEDROCK=1 set. The stream watchdogs run independently of it and abort a long silent pause even when you set 0 hereAPI_TIMEOUT_MS
Other
Time in milliseconds that each API request attempt has to receive its response headers. It doesn't limit how long a streaming response runs after that. The default is 600000, or 10 minutes, and the maximum is 2147483647. When you set a positive value, each attempt at a non-streaming request has to finish within it. Increase this when requests time out on slow networks or when routing through a proxy. Set to
0 to remove this limit, which requires Claude Code v2.1.305 or later. With 0, a non-streaming attempt still times out after 300 seconds in a local sessionAWS_BEARER_TOKEN_BEDROCK
Cloud providers
Amazon Bedrock API key for authentication (see Amazon Bedrock API keys)
BASH_DEFAULT_TIMEOUT_MS
Shell & Bash
Default timeout for a foreground Bash or PowerShell tool command, in milliseconds (default: 120000, or 2 minutes). A value above the default time limit for background commands replaces that default in unattended sessions. The background time limit requires Claude Code v2.1.285 or later
BASH_MAX_OUTPUT_LENGTH
Shell & Bash
Maximum number of characters of bash output that Claude Code reads back into a command's result (default: 30000; maximum: 150000). If you set the
bashOutputMaxChars setting, Claude Code ignores this variable. See Output limitsBASH_MAX_TIMEOUT_MS
Shell & Bash
Maximum timeout the model can set for a foreground Bash or PowerShell tool command, in milliseconds (default: 600000, or 10 minutes). The effective ceiling is the larger of this and
BASH_DEFAULT_TIMEOUT_MS. An effective ceiling longer than 2 hours also becomes the maximum time limit for background commands in unattended sessions. The background time limit requires Claude Code v2.1.285 or laterOTLP/HTTP endpoint for detailed beta tracing: with
ENABLE_BETA_TRACING_DETAILED=1, logs and traces go there instead of to the configured exporters. Set it in your shell, user settings, or managed settings. Ignored in project and local settingsCCR_FORCE_BUNDLE
Other
Set to
1 to force claude --cloud to bundle and upload your local repository instead of cloning from its remoteCLAUDECODE
Other
Set to
1 in subprocesses Claude Code spawns (Bash and PowerShell tools, tmux sessions, hook commands, status line commands, stdio MCP server subprocesses). IDE extensions also set this in their integrated terminals. Use to detect when a script is running inside a subprocess spawned by Claude Code. To check whether the current process was spawned directly by a tool call or hook, rather than inside a stdio MCP server that Claude Code started, use CLAUDE_CODE_CHILD_SESSION insteadCLAUDE_AGENT_SDK_DISABLE_BUILTIN_AGENTS
Disable features
Set to
1 to disable all built-in subagent types such as Explore and Plan. Only applies in non-interactive mode (the -p flag). Useful for SDK users who want a blank slate. This also removes general-purpose, the subagent Claude Code runs when an Agent tool call omits subagent_type. Such a call then fails with subagent_type is requiredSet to
1 to skip the mcp__<server>__ prefix on tool names from SDK-created MCP servers. Tools use their original names. SDK usage onlyStall timeout in milliseconds for subagents. Also covers workflow agents on Claude Code v2.1.286 or later. Default
600000 (10 minutes); if you raise CLAUDE_STREAM_IDLE_TIMEOUT_MS while the stream watchdog is on, the default rises with it, as Handle slow or stalled API responses describesCLAUDE_AUTOCOMPACT_PCT_OVERRIDE
CLAUDE_*
Set the percentage (1-100) of the auto-compact window at which auto-compaction triggers. Use lower values like
50 to compact earlier; the variable can't raise the threshold, so values above the default percentage are ignored. It applies only in sessions that compact before the model's context limit. Applies to both main conversations and subagentsCLAUDE_AUTO_BACKGROUND_TASKS
CLAUDE_*
Set to
1 to force-enable automatic backgrounding of long-running agent tasks. When enabled, a subagent moves to the background after running for approximately two minutes. If Claude queued a tool call such as a file edit behind the subagent, the subagent finishes in the foreground before that call starts. Also enables automatic backgrounding of long MCP tool calls in non-interactive mode on Claude Code v2.1.212 or laterCLAUDE_AX_PREPARK_MS
CLAUDE_*
In screen reader mode, how many milliseconds Claude Code waits before it writes a new or changed line. Default
0, so Claude Code doesn't wait. Before v2.1.287, the default was 50. Claude Code caps the wait at 5000. Ignored in project and local settings. Requires Claude Code v2.1.233 or laterCLAUDE_AX_SCREEN_READER
CLAUDE_*
Set to
1 to render screen-reader friendly output: flat text without decorative borders or animations. Set to 0 to force screen-reader mode off even when axScreenReader is true. The --ax-screen-reader flag takes precedence. Ignored in project and local settings. Requires Claude Code v2.1.181 or laterCLAUDE_AX_STARTUP_QUIET_MS
CLAUDE_*
In screen reader mode, how many milliseconds Claude Code holds the first interface render after the startup confirmation line. Your screen reader can then speak the line in full before new output interrupts it. Default
3000. Set 0 to render immediately. Claude Code caps the hold at 600000 (10 minutes). Your first keystroke ends the hold early. Ignored in project and local settings. Requires Claude Code v2.1.217 or laterReturn to the original working directory after each Bash or PowerShell command in the main session
Timeout in milliseconds for the byte-level streaming idle watchdog; when set, it takes precedence over
CLAUDE_STREAM_IDLE_TIMEOUT_MS for that watchdog and leaves the event-level watchdog unchanged. Claude Code clamps this variable to between 10 seconds and 30 minutes. Requires Claude Code v2.1.210 or laterCLAUDE_CLIENT_PRESENCE_FILE
CLAUDE_*
Path to a file that an external tool, such as a screen-lock listener, creates when you unlock your screen and deletes when you lock it. While the file exists, Claude Code skips Remote Control mobile push notifications, so you stop getting pushes while you are actively using the computer. When the file is absent or unreadable, notifications are sent as normal. Claude Code checks the file once per push-triggering event rather than polling it. Requires Claude Code v2.1.181 or later
CLAUDE_CODE_ACCESSIBILITY
CLAUDE_*
Set to
1 to keep the native terminal cursor visible and disable the inverted-text cursor indicator. Allows screen magnifiers like macOS Zoom to track cursor positionSet to
1 to load memory files from directories specified with --add-dir. Loads CLAUDE.md, .claude/CLAUDE.md, .claude/rules/*.md, and CLAUDE.local.md. By default, additional directories do not load memory filesSet to
1 to repaint the entire screen on every frame in fullscreen rendering instead of sending incremental updates. Use this if fullscreen mode shows stale or misplaced text fragments. Claude Code enables this automatically for background sessions and agent view on WindowsCLAUDE_CODE_ALWAYS_ENABLE_EFFORT
CLAUDE_*
Set to
1 to send the effort parameter with every request, even when Claude Code does not recognize the model ID as effort-capable. Use this when routing through an LLM gateway or third-party provider that serves models under custom identifiers. Models that reject the effort parameter at the API, including Claude Opus 4.1, Claude Sonnet 4.5, Claude Haiku 4.5, and earlier models, are still excluded so requests do not failInterval in milliseconds at which credentials should be refreshed (when using
apiKeyHelper)CLAUDE_CODE_ARTIFACT_AUTO_OPEN
CLAUDE_*
Set to
0 to stop Claude Code from opening the browser automatically when a new artifact is publishedCLAUDE_CODE_ARTIFACT_COMMENTS
CLAUDE_*
Set to
0 to stop Claude reading and replying to comments on an artifact. Has no effect when CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC has turned artifacts off. Requires Claude Code v2.1.221 or laterSet to
0 to stop Claude replying on its own to comments sent to it. Requires Claude Code v2.1.228 or laterSet to
0 to stop Claude from applying small changes to an artifact's file as part of publishing it. Claude then edits the file with its file-editing tools and publishes it as a separate step. Requires Claude Code v2.1.300 or laterCLAUDE_CODE_ATTRIBUTION_HEADER
CLAUDE_*
Set to
0 to omit the attribution block, which carries the client version and a prompt fingerprint, from the start of the system prompt. Caching on a direct connection to the Anthropic API is unaffected either way. In some direct-connection setups, Claude Code keeps the block on auto mode classifier requests even when you set 0. In System prompt attribution block, check which connections and credentials this covers. Before v2.1.181 the block included a per-request token on custom base URLs and Microsoft Foundry connections, so on those versions set it to 0 when your LLM gateway caches on the request body or forwards requests to a third-party provider, or when you connect to Microsoft Foundry directlyRemoved in v2.1.283. Use
CLAUDE_CODE_WORKER_CHECKIN_SCHEDULE insteadCLAUDE_CODE_AUTO_COMPACT_WINDOW
CLAUDE_*
Set the auto-compact window, how full the context gets before compaction, from
100000 to 1000000 tokens. Suffixed values such as 200k require v2.1.304 or later. For precedence over the other ways to set the window and the effect on the status line's used_percentage, see Set the auto-compact windowCLAUDE_CODE_AUTO_CONNECT_IDE
CLAUDE_*
Override automatic IDE connection. By default, Claude Code connects automatically when launched inside a supported IDE's integrated terminal. Set to
false to prevent this. Set to true to force a connection attempt when auto-detection fails, such as when tmux obscures the parent terminal. Takes precedence over the autoConnectIde global config settingCLAUDE_CODE_AUTO_MODE_MODEL
CLAUDE_*
Sets the model for the classifier requests Claude Code sends in auto mode. Use a full model ID such as
claude-sonnet-4-6. For the cases where Claude Code ignores it, see Choose the classifier model. Requires Claude Code v2.1.302 or laterCLAUDE_CODE_AUTO_MODE_SERVER
CLAUDE_*
Controls whether Claude Code asks the server to review auto mode actions. Set to
0 to use Claude Code's own classifier requests instead. On a direct connection to the Anthropic API, requires v2.1.281 or later. The linked section lists which sessions ask the server when the variable is unset, and from which version. Requires Claude Code v2.1.271 or laterCLAUDE_CODE_AWS_CHAIN_RESOLVE_TIMEOUT_MS
Cloud providers
Time in milliseconds Claude Code waits for the AWS default credential provider chain to produce credentials before the request fails with
AWS default-chain credential resolve timed out (default: 60000). Raise it when a step in your chain legitimately needs longer, such as a browser-based SSO sign-in with MFA through a wrapper like aws-vault. Applies on Amazon Bedrock, Claude Platform on AWS, and the Mantle endpoint. See credential caching and resolution timeout. Requires Claude Code v2.1.207 or laterCLAUDE_CODE_BASH_EDIT_DIFF
CLAUDE_*
Set to
0 to turn off the diff of the files that changed while a Bash command ran, or 1 to record it in every permission mode. Takes precedence over the bashEditDiffEnabled setting. Requires Claude Code v2.1.269 or laterSet to
0 to make a non-interactive session report an idle status to its host at every turn end, even while background work is still running. By default, the session keeps reporting a running status past turn end while background work such as a background agent or a workflow run is still live. This keeps a host that watches the status, such as a remote session list, from announcing that Claude is waiting for your input mid-work. Background shell commands, such as a dev server, don't hold the running status. The running-status default and the 0 opt-out require Claude Code v2.1.269 or later; on earlier versions, set 1 to hold the running statusCLAUDE_CODE_BRIDGE_SESSION_ID
CLAUDE_*
Set automatically in Bash tool and hook command subprocesses while the session has an active Remote Control connection, and removed when the connection ends. The value is the session's ID in
session_ form, the same identifier that appears in the session's claude.ai/code URL, so a script can link back to the session that ran it. Requires Claude Code v2.1.199 or later. In cloud sessions, read CLAUDE_CODE_REMOTE_SESSION_ID insteadCLAUDE_CODE_BS_AS_CTRL_BACKSPACE
CLAUDE_*
Set to
0 to make Claude Code read the 0x08 byte, also written ^H, as plain Backspace, or 1 to read it as Ctrl+Backspace. Either value replaces the platform default. By default, Claude Code reads it as Ctrl+Backspace on Windows, except when TERM_PROGRAM is mintty or TERM is cygwin, and as plain Backspace on macOS and Linux. Set 0 in a Windows terminal where Backspace deletes a whole wordCLAUDE_CODE_CERT_STORE
Network & proxy
Comma-separated list of CA certificate sources for TLS connections.
bundled is the Mozilla CA set shipped with Claude Code. system is the operating system trust store, read only on runtimes with tls.getCACertificates: the native binary, or Node 22.15 or later for npm installs. See CA certificate store. Default is bundled,systemCLAUDE_CODE_CHILD_SESSION
CLAUDE_*
Set to
1 in subprocesses Claude Code spawns via the Bash, PowerShell, and Monitor tools, hook commands, and status line commands. Not set for stdio MCP server subprocesses, which are long-lived and outlive the session that spawned them. Unlike CLAUDECODE, this is only set by Claude Code itself when it launches a subprocess and not by IDE extensions, so it reliably distinguishes a nested session from a top-level claude launched in an IDE-integrated terminal. A nested interactive claude TUI started this way is automatically excluded from --resume, --continue, up-arrow history, and the claude agents list. Non-interactive claude -p sessions still persist. Set CLAUDE_CODE_FORCE_SESSION_PERSISTENCE=1 to override this exclusion. Requires Claude Code v2.1.172 or laterCLAUDE_CODE_CLIENT_CERT
Network & proxy
Path to client certificate file for mTLS authentication
CLAUDE_CODE_CLIENT_KEY
CLAUDE_*
Path to client private key file for mTLS authentication
Passphrase for encrypted CLAUDE\_CODE\_CLIENT\_KEY (optional)
CLAUDE_CODE_CONNECT_TIMEOUT_MS
CLAUDE_*
Removed in v2.1.186 and now a no-op. Previously set a separate timeout for the connect, TLS, and response-header phase of a streaming API request. Use
API_TIMEOUT_MS instead. For the response-header phase of a streaming request, see CLAUDE_STREAM_FIRST_BYTE_TIMEOUT_MSCLAUDE_CODE_DEBUG_LOGS_DIR
CLAUDE_*
Override the debug log file path. Despite the name, this is a file path, not a directory. Requires debug mode to be enabled separately via
--debug, /debug, or the DEBUG environment variable: setting this variable alone does not enable logging. The --debug-file flag does both at once. Defaults to ~/.claude/debug/<session-id>.txtCLAUDE_CODE_DEBUG_LOG_LEVEL
CLAUDE_*
Minimum log level written to the debug log file. Values:
verbose, debug (default), info, warn, error. Set to verbose to include high-volume diagnostics like full status line command output, or raise to error to reduce noiseCLAUDE_CODE_DISABLE_1M_CONTEXT
Disable features
Set to
1 to turn off 1M context window support. Claude Code removes [1m] model variants from the model picker and holds models that run with the 1M window by default to a 200K window. See Turn off 1M context. Useful for enterprise environments with compliance requirements. For its role in correcting the window for an unrecognized [1m] model ID, see Correct the window for a gateway or custom model IDCLAUDE_CODE_DISABLE_ADAPTIVE_THINKING
Disable features
Set to
1 to disable adaptive reasoning on Opus 4.6 and Sonnet 4.6 and fall back to the fixed thinking budget controlled by MAX_THINKING_TOKENS. Has no effect on Fable models, Sonnet 5 and later, Haiku 5.5, or Opus 4.7 and later, which always use adaptive reasoningCLAUDE_CODE_DISABLE_ADVISOR_TOOL
Disable features
Set to
1 to disable the advisor tool. The /advisor command becomes unavailable, any configured advisorModel is ignored, and the --advisor flag is accepted but has no effect, so existing scripts that pass it continue to work without errorsCLAUDE_CODE_DISABLE_AGENT_VIEW
Disable features
Set to
1 to turn off background agents and agent view: claude agents, --bg, /background, and the on-demand supervisor. Equivalent to the disableAgentView settingCLAUDE_CODE_DISABLE_ALTERNATE_SCREEN
Disable features
Set to
1 to disable fullscreen rendering and use the classic main-screen renderer. The conversation stays in your terminal's native scrollback so Cmd+f and tmux copy mode work as usual. Takes precedence over CLAUDE_CODE_NO_FLICKER and the tui setting. You can also switch with /tui default. Does not apply to background sessions opened from agent view, which always use fullscreen renderingCLAUDE_CODE_DISABLE_ARTIFACT
Disable features
Set to
1 to turn off the Artifact tool, which publishes session output as a private web page on claude.ai. Once you set it, no settings file turns the tool back on. To turn the tool off from a settings file instead, set enableArtifact to false; the deprecated disableArtifact key also turns it offCLAUDE_CODE_DISABLE_ATTACHMENTS
Disable features
Set to
1 to disable attachment processing. File mentions with @ syntax are sent as plain text instead of being expanded into file content. Ignored in project and local settingsCLAUDE_CODE_DISABLE_AUTH_REFRESH_LOCK
Disable features
Set to
1 to make a Claude Code process run its gcpAuthRefresh or awsAuthRefresh command itself instead of waiting while another process runs it. Requires Claude Code v2.1.286 or laterCLAUDE_CODE_DISABLE_AUTO_MEMORY
Disable features
Set to
1 to disable auto memory. Set to 0 to force auto memory on even when --bare mode or autoMemoryEnabled: false would otherwise disable it. When disabled, Claude does not create or load auto memory filesCLAUDE_CODE_DISABLE_BACKGROUND_TASKS
Disable features
Set to
1 to remove the run_in_background parameter from the Bash, PowerShell, and subagent tools and to turn off the Ctrl+B shortcut and background runs of forked skills. Claude Code then also stops moving subagents, long MCP tool calls, and timed-out shell commands to the background automatically. MCP tasks and the Monitor tool still run in the background. To turn off background sessions too, set CLAUDE_CODE_DISABLE_AGENT_VIEW to 1CLAUDE_CODE_DISABLE_BEDROCK_CONTENT_TYPE_DEFAULT
Cloud providers
Set to
1 to stop Claude Code from treating an Amazon Bedrock streaming response with a missing or empty Content-Type header as Amazon Bedrock's binary event stream. By default, Claude Code assumes a gateway dropped the header from an otherwise unmodified response, so it decodes the body and streaming keeps working. Set this only for a gateway that also re-emits the stream as server-sent events; Claude Code then reads the header-less body as server-sent events instead. Requires Claude Code v2.1.239 or laterCLAUDE_CODE_DISABLE_BEDROCK_CONTENT_TYPE_GUARD
Cloud providers
Set to
1 to skip the check that an Amazon Bedrock streaming response carries the application/vnd.amazon.eventstream content-type. Without this variable, when a response carries a different content-type, Claude Code fails the request with an error naming that type, which means a gateway or proxy is transforming the response. Configure the gateway to forward the Content-Type header and body unmodified rather than setting this variable. Requires Claude Code v2.1.208 or laterCLAUDE_CODE_DISABLE_BG_EXIT_HANDOFF
Disable features
Set to
1 to stop a background session's in-flight work when the supervisor stops, restarts, or updates that session's process, instead of handing it to the session's next process. That work is the session's running background shell commands, plus background subagents as of v2.1.198. Affects only that handoff: backgrounding a session with ← or /background still carries in-flight background work over. Requires Claude Code v2.1.196 or laterCLAUDE_CODE_DISABLE_BG_SHELL_PRESSURE_REAP
Disable features
Set to
1 to stop Claude Code from terminating background shell commands under memory pressure. By default, on macOS and Linux, Claude Code terminates background shells when the operating system reports critical memory pressure and the session has been idle for 30 minutes with no turn or subagent running. Windows has no memory-pressure signal, so this variable has no effect there. Requires Claude Code v2.1.193 or laterCLAUDE_CODE_DISABLE_BUNDLED_SKILLS
Disable features
Set to
1 to disable the skills and workflows included with Claude Code: bundled skills and workflows are removed entirely, while built-in commands like /init stay typable but are hidden from the model. /doctor stays typable like the built-in commands; hide it with DISABLE_DOCTOR_COMMAND instead. Skills from plugins, .claude/skills/, and .claude/commands/ are unaffected. Equivalent to the disableBundledSkills settingCLAUDE_CODE_DISABLE_CFC_PROMPT
Disable features
For hosts that embed Claude Code and supply their own browser guidance. Set to
1 to keep the Claude in Chrome browser tools available while omitting the Chrome section of the system prompt and the /claude-in-chrome bundled skill. In VS Code, the extension at v2.1.314 or later also leaves the Claude in Chrome instructions out of a session's messages. Requires Claude Code v2.1.257 or laterCLAUDE_CODE_DISABLE_CLAUDE_MDS
Disable features
Set to
1 to prevent loading any CLAUDE.md memory files into context, including user, project, and auto memory filesCLAUDE_CODE_DISABLE_CRON
Disable features
Set to
1 to disable session-scoped scheduled tasks. The /loop skill and cron tools become unavailable and any already-scheduled tasks stop firing, including tasks that are already running mid-sessionCLAUDE_CODE_DISABLE_DANGEROUS_RM_TIMEOUT
Disable features
Set to
1 to turn off the auto and bypassPermissions time limit and denials on critical-path removals. These removals then go to the classifier in auto mode, and get an untimed prompt in bypassPermissions mode wherever Claude Code can show one. Set it in the environment that launches Claude Code, since Claude Code ignores a copy delivered through a settings env block. Requires Claude Code v2.1.281 or laterCLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS
Disable features
Set to
1 to strip pre-release anthropic-beta request headers, the body fields that pair with them, and beta tool-schema fields such as defer_loading and eager_input_streaming from API requests. Use this when a proxy gateway rejects requests with an Unexpected value(s) error for the anthropic-beta header or an Extra inputs are not permitted error. Disable pre-release capabilities lists what the variable removes, including MCP tool search, and what Claude Code keeps sendingCLAUDE_CODE_DISABLE_EXPLORE_PLAN_AGENTS
Disable features
Set to
1 to disable the built-in Explore and Plan subagents. Claude explores with its search tools or the general-purpose subagent instead, and plan mode reads files directly rather than launching Explore and Plan agents. Custom subagents named Explore or Plan are unaffected. To remove every built-in subagent type in the Agent SDK or non-interactive mode, use CLAUDE_AGENT_SDK_DISABLE_BUILTIN_AGENTS instead. Requires Claude Code v2.1.198 or laterCLAUDE_CODE_DISABLE_FAST_MODE
Disable features
Set to
1 to disable fast modeCLAUDE_CODE_DISABLE_FEEDBACK_SURVEY
Disable features
Set to
1 to disable the "How is Claude doing?" session quality surveys. Surveys are also disabled when DISABLE_TELEMETRY, DO_NOT_TRACK, or CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC is set, unless CLAUDE_CODE_ENABLE_FEEDBACK_SURVEY_FOR_OTEL opts back in. To set a sample rate instead of disabling outright, use the feedbackSurveyRate setting. See Session quality surveysCLAUDE_CODE_DISABLE_FILE_CHECKPOINTING
Disable features
Set to
1 to disable file checkpointing. The /rewind command will not be able to restore code changes. Overrides the fileCheckpointingEnabled settingCLAUDE_CODE_DISABLE_FILE_MENTIONS
Disable features
Set to
1 to stop Claude Code from expanding @ mentions of files and directories. Claude instead gets the mentioned paths with a note to read them using its file tools. Ignored in project and local settings. Requires Claude Code v2.1.299 or laterCLAUDE_CODE_DISABLE_GIT_INSTRUCTIONS
Disable features
Set to
1 to remove built-in commit and PR workflow instructions and the git status snapshot from Claude's context. Useful when using your own git workflow skills. Takes precedence over the includeGitInstructions setting when setCLAUDE_CODE_DISABLE_INLINE_SHELL_RM_PROMPT
Disable features
Set to
1 to stop Claude Code from reading scripts passed to a shell with -c, such as bash -c 'rm -rf ~', for critical-path removals. Claude Code still checks the shell variable and positional parameter targets in those scripts, and the other critical-path checks keep running. Set it in the environment that launches Claude Code, since Claude Code ignores a copy delivered through a settings env block. Requires Claude Code v2.1.288 or laterCLAUDE_CODE_DISABLE_LEGACY_MODEL_REMAP
Disable features
Set to
1 to prevent automatic remapping of Opus 4 and Opus 4.1 to the current Opus version on the Anthropic API. Use when you intentionally want to pin an older model. The remap does not run on Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft FoundrySet to
1 so that Claude waits for the result of an MCP task in an interactive session. While automatic backgrounding is on, it still moves the call to the background after two minutes by default. Requires Claude Code v2.1.304 or laterCLAUDE_CODE_DISABLE_MODEL_ACCESS_FALLBACK
Disable features
Set to
1 to stop Claude Code on Amazon Bedrock and Google Cloud's Agent Platform from switching to an older model when your account loses access to a session's model mid-session; the refused request fails at once instead. A fallback model chain you configure still switches on that refusal, and the startup model checks still fall back at launch. Requires Claude Code v2.1.285 or laterCLAUDE_CODE_DISABLE_MOUNTED_DRIVE_RM_PROMPT
Disable features
Set to
1 to turn off the mounted drive prompt for paths such as /Volumes/USB. Set it in the environment that launches Claude Code, because Claude Code ignores it in a settings env block. Requires Claude Code v2.1.304 or laterCLAUDE_CODE_DISABLE_MOUSE
Disable features
Set to
1 to disable mouse tracking in fullscreen rendering. Keyboard scrolling with PgUp and PgDn still works. Use this to keep your terminal's native copy-on-select behaviorCLAUDE_CODE_DISABLE_MOUSE_CLICKS
Disable features
Set to
1 to disable click, drag, and hover handling in fullscreen rendering while keeping mouse-wheel scrolling. Use this when you want wheel scroll to work inside Claude Code but don't want clicks to position the cursor, expand tool output, or open links. CLAUDE_CODE_DISABLE_MOUSE takes precedence when both are set. Requires Claude Code v2.1.195 or laterCLAUDE_CODE_DISABLE_MTLS_RELOAD_ON_STALE_CONNECTION
Disable features
Set to
1 to stop Claude Code from re-reading the mTLS client certificate and key when an API request fails with a connection-level error, such as a connection reset or a TLS handshake error. With the reload disabled, Claude Code loads rotated files only when it next applies settings or at the next startup. Requires Claude Code v2.1.232 or laterCLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC
Disable features
Set to any non-empty value, such as
1, to disable nonessential network traffic: auto-updates, telemetry, error reporting, the /feedback command, Claude-drafted feedback, release notes, the PR and MR status badge checks, and availability checks such as the fast mode check. It also stops the background runs of plugin command sources, which are local commands rather than network traffic, because they can trigger dependency installs. Setting it to `0` or `false` still disables this traffic, unlike most on/off variables; unset the variable to allow it again. Also disables feature-flag fetching, which makes Remote Control and the other features that need feature-flag fetching unavailable. Official plugin marketplace auto-install isn't covered; disable it with CLAUDE_CODE_DISABLE_OFFICIAL_MARKETPLACE_AUTOINSTALL. Doesn't affect gateway model discovery, which has its own opt-inCLAUDE_CODE_DISABLE_NONSTREAMING_FALLBACK
Disable features
Set to
1 to disable the non-streaming fallback when a streaming request fails mid-stream. Streaming errors propagate to the retry layer instead. Useful when a proxy or gateway causes the fallback to produce duplicate tool executionCLAUDE_CODE_DISABLE_NOTIFICATION_PRESENCE_CHECK
Disable features
Set to
1 to send the PushNotification tool's desktop notification even while you are typing in or focused on the terminal. By default the tool skips both the desktop notification and the mobile push when it detects recent keyboard activity or terminal focus. This variable disables only that local check, so the server can still suppress the mobile push when it detects that you are active. Requires Claude Code v2.1.193 or laterCLAUDE_CODE_DISABLE_OFFICIAL_MARKETPLACE_AUTOINSTALL
Disable features
Set to
1 to disable automatic registration of the official plugin marketplace. Claude Code reads the variable when it is about to register the marketplace, usually during a machine's first interactive launch. If the variable is set at that point, Claude Code skips the registration permanently. Unsetting the variable later doesn't undo the skip. Run claude plugin marketplace add anthropics/claude-plugins-official to register the marketplace at any timeCLAUDE_CODE_DISABLE_PERMISSION_PROMPT_NOTIFY_HOOKS
Disable features
Set to
1 to stop Claude Code from running your Notification hooks for unanswered permission requests in sessions where Claude Code sends them to the Agent SDK's canUseTool callback, which is how Claude Desktop and the VS Code extension host Claude Code. Has no effect in terminal sessions. Requires Claude Code v2.1.233 or laterCLAUDE_CODE_DISABLE_POLICY_SKILLS
Disable features
Set to
1 to skip loading skills from the system-wide managed skills directory. Useful for container or CI sessions that should not load operator-provisioned skillsCLAUDE_CODE_DISABLE_POWERSHELL_CMD_RM_DENY
Disable features
Set to
1 to turn off the PowerShell tool check that denies the cmd built-ins rd, rmdir, del, and erase on a system path, such as a drive root or your home directory. Claude Code ignores this variable in a settings file's env block. Requires Claude Code v2.1.283 or laterCLAUDE_CODE_DISABLE_REFUSAL_FALLBACK
Disable features
Set to
1 to turn off the automatic model switch when a safety classifier flags a request, the behavior the switchModelsOnFlag setting controlsCLAUDE_CODE_DISABLE_STRUCTURED_OUTPUTS
Disable features
Set to
1 to stop Claude Code from sending the structured-output output_config.format field and the anthropic-beta value that pairs with it, for an LLM gateway whose upstream rejects them. This leaves on the other pre-release capabilities that CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS turns off. Requires Claude Code v2.1.288 or laterCLAUDE_CODE_DISABLE_SUBSTITUTION_RM_PROMPT
Disable features
Set to
1 to turn off the critical-path check for a recursive rm whose target is entirely the output of a command substitution, such as rm -rf "$(pwd)". The other critical-path checks keep running. Set it in the environment that launches Claude Code, since Claude Code ignores a copy delivered through a settings env block. Requires Claude Code v2.1.281 or laterCLAUDE_CODE_DISABLE_TERMINAL_TITLE
Disable features
Set to
1 to disable automatic terminal title updates based on conversation context. This also skips the background small/fast-model request that generates a session title, and turns off status reports to your terminalCLAUDE_CODE_DISABLE_THINKING
Disable features
Set to
1 to omit the thinking parameter from API requests entirely. This is a compatibility option for proxies and gateways that reject the parameter. On models that think by default, omitting the parameter means the model may still think. To explicitly disable extended thinking on the Anthropic API, use MAX_THINKING_TOKENS=0 instead. Neither variable turns thinking off on Opus 5.5, Sonnet 5.5, Haiku 5.5, or the Fable models, which can't have thinking turned off. On third-party providers, MAX_THINKING_TOKENS=0 likewise omits the parameter, so the two variables behave the same thereCLAUDE_CODE_DISABLE_ULTRAREVIEW_TRUST_CHECK
Disable features
Set to
1 so that claude ultrareview doesn't exit with Error: Workspace not trusted in a folder you haven't trusted when it can't ask you to trust it, such as in CI. Set it in the environment that launches Claude Code, not a settings env block, and only where every such run starts in a folder you trust. Runs that can ask still ask. Requires Claude Code v2.1.309 or laterCLAUDE_CODE_DISABLE_UNKNOWN_MODEL_WINDOW_ENFORCEMENT
Disable features
Set to
1 to skip proactive auto-compaction when Claude Code doesn't recognize the model ID, such as an LLM gateway alias. Without this variable, Claude Code compacts at the context window it assumes for the ID. CLAUDE_CODE_MAX_CONTEXT_TOKENS can correct the assumed window instead; see Correct the window for a gateway or custom model ID for when each variable applies. Requires Claude Code v2.1.223 or laterCLAUDE_CODE_DISABLE_VIRTUAL_SCROLL
Disable features
Set to
1 to disable virtual scrolling in fullscreen rendering and render every message in the transcript. Use this if scrolling in fullscreen mode shows blank regions where messages should appearCLAUDE_CODE_DISABLE_WEB_FETCH
Disable features
CLAUDE_CODE_DISABLE_WINDOWS_SHELL_LAUNCHER
Disable features
Set to
1 to start PowerShell tool commands on Windows directly instead of through the cmd.exe launcher. By default, the launcher lets a PowerShell command running in the background carry over to the session's next process, such as when you background the session. If you set the variable, a backgrounded PowerShell command stops when the session's process exits. Bash commands aren't affected. Requires Claude Code v2.1.269 or laterCLAUDE_CODE_DISABLE_WORKFLOWS
Disable features
Set to
1 to disable workflows. Equivalent to the disableWorkflows settingCLAUDE_CODE_EFFORT_LEVEL
CLAUDE_*
Set the effort level for supported models. Values:
low, medium, high, xhigh, or max. Available levels depend on the model. Takes precedence over --effort, /effort, and the modelSettings and effortLevel settings. A maxEffortLevel cap still applies. Set it to auto or unset to have Claude Code send no effort level, so that the API applies its own default for the model. See Adjust effort levelSet to
1 to add session_state_changed messages, which carry the session's state, to the message stream. Requires either the Agent SDK or --print, --output-format stream-json, and --verboseCLAUDE_CODE_ENABLE_AUTO_MODE
CLAUDE_*
Accepted for compatibility with older releases and has no effect. Auto mode is available by default on every provider, including Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry, and signed-in Claude apps gateway sessions. In v2.1.158 through v2.1.206, setting this to
1 was required to make auto mode available on those providersCLAUDE_CODE_ENABLE_AWAY_SUMMARY
CLAUDE_*
Override session recap availability. Set to
0 to force recaps off regardless of the /config toggle. Set to 1 to force recaps on when awaySummaryEnabled is false. Takes precedence over the setting and /config toggleSet to
1 to refresh plugin state at turn boundaries in non-interactive mode after a background install completes. Off by default because the refresh changes the system prompt mid-session, which invalidates prompt caching for that turnCLAUDE_CODE_ENABLE_CFC
CLAUDE_*
Set to
1 to start a CLI session with Chrome integration on, or 0 to start with it off. Takes precedence over the claudeInChromeDefaultEnabled setting. The --chrome and --no-chrome flags take precedence over both. Claude Code ignores 1 in project and local settingsSet to
1 to route the "How is Claude doing?" session quality survey to your own OpenTelemetry collector when Anthropic-bound nonessential traffic is blocked. Survey ratings are emitted only as OTEL events to your configured collector. No survey data is sent to Anthropic in this mode. Applies when CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC, DISABLE_TELEMETRY, or DO_NOT_TRACK is set, and has no effect otherwise. CLAUDE_CODE_DISABLE_FEEDBACK_SURVEY and the organization product feedback policy take precedenceControls whether tool call inputs stream from the API as Claude generates them. With this off, a large tool input such as a long file write arrives only after Claude finishes generating it, which can look like it's hanging. Enabled by default on the Anthropic API. On Amazon Bedrock and Google Cloud's Agent Platform, enabled per model where the deployed container supports it. Set to
0 to opt out. Set to 1 to force on when routing through a proxy via ANTHROPIC_BASE_URL, ANTHROPIC_VERTEX_BASE_URL, or ANTHROPIC_BEDROCK_BASE_URL. Off by default on Microsoft Foundry and gateway connectionsSet to
1 to populate the /model picker from your gateway's /v1/models endpoint when ANTHROPIC_BASE_URL points at an Anthropic-compatible gateway such as LiteLLM, Kong, or an internal proxy. Off by default because gateways backed by a shared API key would otherwise show every user every model the key can access. Discovered models are still filtered by an availableModels allowlist the session receives; deliver the list through MDM or a managed settings file, since server-managed delivery is not available on gateway configurationsRemoved in v2.1.142, when the fast mode default moved from Opus 4.6 to Opus 4.7
Set to
false to turn off prompt suggestions, the grayed-out predictions that appear in your prompt input. Takes precedence over the promptSuggestionEnabled setting, which is what the Prompt suggestions toggle in /config writes. Claude Code also pauses suggestions while your account is close to or at its usage limit. Set to true to keep that pause from applying until you reach the limit. Requires Claude Code v2.1.238 or later. See Prompt suggestionsCLAUDE_CODE_ENABLE_TASKS
CLAUDE_*
Selects which task-tracking tools Claude Code provides in sessions that have them. By default, Claude Code provides the Task tools
TaskCreate, TaskUpdate, TaskGet, and TaskList. Set to 0 to get the legacy TodoWrite tool instead. See Task listCLAUDE_CODE_ENABLE_TELEMETRY
Telemetry
Set to
1 to enable OpenTelemetry data collection for metrics and logging. Required before configuring OTel exporters. Set it in your shell, user settings, or managed settings. Ignored in project and local settings. See MonitoringCLAUDE_CODE_ENABLE_TODO_TOOLS
CLAUDE_*
Set to
1 to get the task-tracking tools on every model. Without it, Claude Code provides them by default only on the models listed under Task tool availability. CLAUDE_CODE_ENABLE_TASKS still selects the Task tools or TodoWrite. Requires Claude Code v2.1.233 or laterSet to
1 to run dangerous rm commands with no prompt in bypassPermissions mode, which removes a safety prompt for destructive deletes. The linked section lists where it has no effect. Set it in the environment that launches Claude Code, because Claude Code ignores it in a settings env block. Requires Claude Code v2.1.311 or laterTime in milliseconds to wait after the query loop becomes idle before automatically exiting. Useful for automated workflows and scripts using SDK mode
Set to
1 to enable agent teams. Agent teams are experimental and disabled by defaultCLAUDE_CODE_EXTRA_BODY
CLAUDE_*
JSON object to merge into the top level of every API request body. Useful for passing provider-specific parameters that Claude Code doesn't expose directly. A value exported in your shell also applies to the background sessions you dispatch with
claude agents or --bg. Before v2.1.206, background sessions ignored a shell-exported value and used whatever copy the background supervisor process inheritedOverride the default token limit for file reads, which is 25,000 tokens. Useful when you need to read larger files in full. A read that Claude makes with the
allow_large parameter can go past this limit when the context window has roomSet to
1 to force transcript persistence, prompt history, and claude agents registration even when this claude was launched from inside another Claude Code session. Use when an inherited CLAUDE_CODE_CHILD_SESSION value, for example from a screen session or a background launcher first started by Claude Code's Bash tool, causes a genuine top-level session to be misclassified as nested. As of v2.1.178, Claude Code detects the tmux case automatically and ignores the inherited marker, so tmux no longer needs this variable. Also honored on v2.1.169 and earlier; has no effect on v2.1.170 and v2.1.171, where the nested-session detection it overrides was removedCLAUDE_CODE_FORCE_STRIKETHROUGH
CLAUDE_*
Set to
1 to force strikethrough rendering for ~~text~~ in Claude's responses when your terminal supports it but is not auto-detected, such as over SSH without TERM_PROGRAM forwarded. Without this, undetected terminals show the literal ~~ markers instead of rendering the text as strikethrough. Requires Claude Code v2.1.186 or laterCLAUDE_CODE_FORCE_SYNC_OUTPUT
CLAUDE_*
Set to
1 to force-enable DEC private mode 2026 synchronized output when your terminal supports it but is not auto-detected. Useful for emulators such as Emacs eat that implement BSU/ESU but do not reply to the capability probe. Has no effect under tmux. Unlike CLAUDE_CODE_NO_FLICKER, which switches to fullscreen rendering, this doesn't change the rendererSet to
1 to draw mod Image elements as pictures when your terminal draws kitty graphics protocol images with Unicode placeholders and you still see an Image's dimmed alt text. See which terminals draw an Image and where not to set this variableCLAUDE_CODE_FORK_SUBAGENT
CLAUDE_*
Controls fork mode, which is on by default and lets Claude start forks on its own. While fork mode is on, Claude also can't wait for a subagent in interactive terminal, VS Code, or desktop sessions on your machine. Set to
0 to turn fork mode off. For versions, see Turn fork mode offSet to
1 to emit subagent text and thinking blocks in claude -p --output-format stream-json output, the same behavior as the --forward-subagent-text flag. Use the variable when a harness invokes claude and can't pass the flag itself. Unlike the flag, which exits with an error outside non-interactive mode with stream-json output, the variable is ignored there so that nested invocations keep working when it's set process-wide. Requires Claude Code v2.1.211 or laterCLAUDE_CODE_GATEWAY_HINT_HEADERS
CLAUDE_*
Set to
1 to send the gateway hint headers, such as x-claude-code-request-class and x-claude-code-compaction, on a custom proxy or a third-party provider such as Amazon Bedrock or Claude Platform on AWS. Set to 0 to stop sending them on every connection, including a direct connection to the Anthropic API, where Claude Code sends them by default. Requires Claude Code v2.1.273 or laterTimeout in milliseconds for the gateway model discovery request that
CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY turns on (default: 3000). Raise it when your gateway needs longer than three seconds to answer /v1/models at startup. Takes plain digits only; 0, negative values, and other spellings keep the default. Requires Claude Code v2.1.269 or laterCLAUDE_CODE_GIT_BASH_PATH
CLAUDE_*
Windows only: path to the Git Bash executable (
bash.exe). Use when Git Bash is installed but not in your PATH. If the path doesn't exist or the file isn't named bash.exe, sh.exe, bash, or sh, Claude Code ignores the variable and auto-detects Git Bash as if it were unset, logging a warning visible with --debug. Before v2.1.219, Claude Code exited at startup when the path didn't exist, and used any existing file as the shell without checking that it was bash or sh. See Windows setupCLAUDE_CODE_GLOB_NO_IGNORE
CLAUDE_*
Set to
false to make the Glob tool respect .gitignore patterns. By default, Glob returns all matching files including gitignored ones. Does not affect @ file autocomplete, which has its own respectGitignore settingCLAUDE_CODE_GLOB_TIMEOUT_SECONDS
CLAUDE_*
Timeout in seconds for Glob and Grep tool searches. Defaults to 20 seconds on most platforms and 60 seconds on WSL
CLAUDE_CODE_GOAL_CHECKIN_MINUTES
CLAUDE_*
How many minutes background work can keep an active goal waiting before Claude Code asks Claude to check on it. Default
30. Set 0 to turn check-ins off. Give whole minutes in plain digits, at most 10080, which is one week. Claude Code treats any other value as unset and uses the default. Requires Claude Code v2.1.234 or laterCLAUDE_CODE_GZIP_REQUEST_BODIES
CLAUDE_*
Set to
0 to turn off gzip compression of Claude API, telemetry, and artifact publish request bodies sent to api.anthropic.com. By default, Claude Code compresses large request bodies on direct connections and skips compression when you send requests through a proxy, configure a client certificate, or set NODE_EXTRA_CA_CERTS. Use 0 if a TLS-inspecting proxy that Claude Code can't detect mishandles compressed requestsCLAUDE_CODE_HIDE_CWD
CLAUDE_*
Set to
1 to hide the working directory in the startup logo. Useful for screenshares or recordings where the path exposes your OS usernameCLAUDE_CODE_IDE_HOST_OVERRIDE
CLAUDE_*
Override the host address used to connect to the IDE extension. By default Claude Code auto-detects the correct address, including WSL-to-Windows routing
Set to
1 to skip auto-installation of IDE extensions. Equivalent to setting autoInstallIdeExtension to falseCLAUDE_CODE_IDE_SKIP_VALID_CHECK
CLAUDE_*
Set to
1 to skip validation of IDE lockfile entries during connection. Use when auto-connect fails to find your IDE despite it runningContext size, in tokens, at which idle compaction applies to a conversation (default:
200000). Accepts a positive whole number, and anything else is ignored. Values below 100000 are raised to 100000, the lowest threshold. Idle compaction is on by default for conversations that meet its conditions. To turn it off, set idleCompaction to false. Requires Claude Code v2.1.290 or laterHow many subagents can be running in one session before the Agent tool refuses to spawn another (default: 20). Accepts a positive whole number in plain digits; anything else is ignored, so the variable can adjust the cap but can't disable it. Requires Claude Code v2.1.217 or later
CLAUDE_CODE_MAX_CONTEXT_TOKENS
CLAUDE_*
Override the context window size Claude Code assumes for the active model. As of v2.1.193, how it applies depends on how Claude Code resolves the model ID; see Correct the window for a gateway or custom model ID. Use this when routing to a model through
ANTHROPIC_BASE_URL whose context window does not match the built-in size for its nameMaximum length in characters of MCP tool descriptions and MCP server instructions that Claude Code sends to the model. The value you set replaces both default limits: 4096, and 16384 for the description of a tool that Claude loads through tool search. Accepts a positive whole number in plain digits. Anything else is ignored and the defaults apply. Requires Claude Code v2.1.280 or later
CLAUDE_CODE_MAX_OUTPUT_TOKENS
CLAUDE_*
Set the maximum number of output tokens for most requests. Defaults and caps vary by model; see max output tokens. Claude Code lowers a value above a model's cap to the cap. For a model ID Claude Code can't resolve to a model it knows, the default is 32000 and the cap is 128000. Increasing this value reduces the effective context window available before auto-compaction triggers
CLAUDE_CODE_MAX_RETRIES
CLAUDE_*
Override the number of times to retry failed API requests (default: 10). Retrying can stop earlier on
529 overloaded errors. For example, with an API key on an Opus model, it stops at the third 529 and shows Repeated 529 Overloaded errors. If you set a fallback model, Claude Code switches to that model rather than showing the error. Capped at 15 as of v2.1.186; as of v2.1.199, CLAUDE_CODE_RETRY_WATCHDOG raises the default and removes the cap. For unattended sessions that need to wait through longer outages, set CLAUDE_CODE_RETRY_WATCHDOG insteadRemoved in v2.1.224 and now a no-op. Previously capped the total number of subagents Claude could spawn with the Agent tool in one session (default: 200); spawning past the cap failed with
Subagent spawn limit reached. The concurrent subagent limit and the depth limit still applyNumber of subagent layers allowed below the main conversation (default: 3). At the default, subagents can spawn their own subagents, and a subagent at the third layer can't spawn further; set
1 to turn nesting off. In v2.1.217 through v2.1.218, the default was 1, so a subagent couldn't spawn its own unless you raised the limit; v2.1.219 raised the default to 3. Accepts a positive whole number in plain digits; anything else is ignored, so the limit can be adjusted but not removed. Requires Claude Code v2.1.217 or laterCLAUDE_CODE_MAX_TURNS
CLAUDE_*
Cap the number of agentic turns when no explicit limit is passed. Equivalent to passing
--max-turns, which takes precedence when both are set. A value that is not a positive integer is rejected at startup with an error rather than treated as no capCap on WebSearch calls (default: 200). When Claude reaches the cap, further WebSearch calls return a notice telling it to continue with the information it already gathered and say so in its answer. Accepts a positive whole number with no upper bound. Anything else is ignored and the default applies, so the cap can be raised but not turned off. Requires Claude Code v2.1.212 or later
Set to
1 to spawn stdio MCP servers with only a safe baseline environment plus the server's configured env, instead of inheriting your shell environmentElapsed time in milliseconds before a still-running MCP tool call moves to a background task (default: 120000, or 2 minutes). Set to
0 to turn automatic backgrounding off and, in an interactive session, to make Claude wait for MCP tasks. Requires Claude Code v2.1.212 or laterHow long in milliseconds the first turn of a non-interactive session waits for MCP servers that are still connecting, in place of the default first-turn wait. In a self-hosted environment, it changes only how long the wait lasts. Some servers keep a wait of their own regardless of the value; Connection timing lists them. Set to
0 to skip the wait for every other server. Requires Claude Code v2.1.274 or laterIdle timeout in milliseconds for MCP tool calls. When a stdio, HTTP, SSE, WebSocket, or claude.ai connector MCP server sends no response and no progress notification for this long, the tool call aborts with an error instead of waiting for the overall
MCP_TOOL_TIMEOUT. Overrides the per-transport defaults of 300000 (5 minutes) for network servers and 1800000 (30 minutes) for stdio servers. Set to 0 to disable the idle check. Values below 1000 are raised to one second, and the value is capped at the effective MCP_TOOL_TIMEOUT. A per-server timeout in .mcp.json of at least 1000 raises that server's idle window to at least the timeout value. Doesn't apply to IDE servers or SDK in-process servers. Requires Claude Code v2.1.187 or later. Before v2.1.203, stdio servers were exempt from the idle timeoutCLAUDE_CODE_MESSAGING_SOCKET
CLAUDE_*
Set by Claude Code, not by you: in sessions that bind an inbox socket, Claude Code exports that socket's path to hooks and Bash commands when it binds the socket. In a session that starts with messaging on, Claude Code binds the socket before any hook runs. Other sessions on the machine deliver messages to this path. Each session exports its own socket rather than one inherited from a parent, and messages arriving on it go through the session's inbound controls. Settings
env blocks can't set it. Requires Claude Code v2.1.224 or laterCLAUDE_CODE_MESSAGING_TOKEN
CLAUDE_*
Set by Claude Code, not by you: in sessions that bind an inbox socket, Claude Code exports this per-session token to hooks and Bash commands alongside
CLAUDE_CODE_MESSAGING_SOCKET. A script posting to the socket can send {"type":"auth","token":"<token>"} as its first line to prove it belongs to the session. On native Windows, Claude Code requires this line and closes any connection that doesn't open with a valid one. The own-child rules say when Claude Code consults the token. Each session exports its own token, never one inherited from a parent session. Settings env blocks can't set it. Requires Claude Code v2.1.228 or laterCLAUDE_CODE_NATIVE_CURSOR
CLAUDE_*
Set to
1 to show the terminal's own cursor at the input caret instead of a drawn block. The cursor respects the terminal's blink, shape, and focus settings. Setting 0 reads the same as leaving the variable unset, so it doesn't bring the drawn block back in a session where the terminal's own cursor is already onCLAUDE_CODE_NEW_INIT
CLAUDE_*
Set to
1 to make /init run an interactive setup flow. The flow asks which files to generate, including CLAUDE.md, skills, and hooks, before exploring the codebase and writing them. Without this variable, /init generates a CLAUDE.md automatically without promptingCLAUDE_CODE_NONBLOCKING_STDOUT
CLAUDE_*
Set to
1 to write terminal output through a second non-blocking file descriptor, so a terminal that stops reading, such as a paused tmux control-mode pane or a stalled SSH connection, can't freeze Claude Code mid-session. Applies on macOS, Linux, and WSL when stdout is a terminal. Requires Claude Code v2.1.261 or laterLimit how many times Claude Code re-sends a non-streaming request that times out. With
0, the request fails on the first timeout. See Tune retry behavior for the timeout. Requires Claude Code v2.1.285 or laterCLAUDE_CODE_NO_FLICKER
CLAUDE_*
Set to
1 to enable fullscreen rendering, a research preview that reduces flicker and keeps memory flat in long conversations. Overrides the tui setting; you can also switch with /tui fullscreenCLAUDE_CODE_OAUTH_REFRESH_TOKEN
CLAUDE_*
OAuth refresh token for claude.ai authentication. When set,
claude auth login exchanges this token directly instead of opening a browser. Requires CLAUDE_CODE_OAUTH_SCOPES. Useful for provisioning authentication in automated environments. Ignored in project and local settingsCLAUDE_CODE_OAUTH_SCOPES
CLAUDE_*
Space-separated OAuth scopes the refresh token was issued with, such as
"user:profile user:inference user:sessions:claude_code". Required when CLAUDE_CODE_OAUTH_REFRESH_TOKEN is set. Ignored in project and local settingsCLAUDE_CODE_OAUTH_TOKEN
CLAUDE_*
OAuth access token for claude.ai authentication. Alternative to
/login for SDK and automated environments. Ignored in project and local settings. Takes precedence over keychain-stored credentials. Generate one with claude setup-token. Unless you run /login, Claude Code uses the token you set for the whole session. To replace an expired token, generate a new one and restartRemoved in v2.1.160 and now a no-op. Previously pinned fast mode to Claude Opus 4.6 instead of the current default. Opus 4.6 no longer supports fast mode
Maximum length of content-bearing OpenTelemetry attributes (model responses, tool content, system prompts, raw API bodies), truncation marker included, in UTF-16 code units (default: 61440, i.e. 60 KB). Raise it only if your telemetry backend accepts attribute values larger than 64 KB, or lower it to cut telemetry volume. Requires Claude Code v2.1.214 or later. See Monitoring
CLAUDE_CODE_OTEL_DIAG_STDERR
CLAUDE_*
Set to
1 to write OpenTelemetry exporter diagnostic errors to stderr. By default these errors only appear with --debug, so a misconfigured exporter such as a Prometheus port collision otherwise fails silently. Requires Claude Code v2.1.179 or later. See MonitoringTimeout in milliseconds for flushing pending OpenTelemetry spans (default: 5000). See Monitoring
Interval for refreshing dynamic OpenTelemetry headers in milliseconds (default: 1740000 / 29 minutes). See Dynamic headers
Timeout in milliseconds for the OpenTelemetry exporter to finish on shutdown (default: 2000). Increase if metrics are dropped at exit. See Monitoring
Starting delay in milliseconds, in place of the default 500, of the exponential backoff between automatic retries of a request that the API rejects with a
529 overloaded error. Raise it to spread the retries over a longer window when the API is at capacity. Give whole milliseconds from 500 to 32000 in plain digits; Claude Code treats any other value as unset. Has no effect when CLAUDE_CODE_RETRY_WATCHDOG is set to 1, or when the rejected request was sent in fast mode. Requires Claude Code v2.1.292 or laterCeiling in milliseconds, in place of the default 32000, on the exponential backoff between automatic retries of a request that the API rejects with a
529 overloaded error. Raise it so that later retries keep spreading apart when the API is at capacity. Give whole milliseconds from 32000 to 64000 in plain digits; Claude Code treats any other value as unset. Has no effect when CLAUDE_CODE_RETRY_WATCHDOG is set to 1, or when the rejected request was sent in fast mode. Requires Claude Code v2.1.296 or laterSet to
1 to let Claude Code run your package manager's upgrade command in the background when a new version is available. Applies to Homebrew and WinGet installations. Other package managers continue to show the upgrade command without running it. See Auto updatesCLAUDE_CODE_PERFORCE_MODE
CLAUDE_*
Set to
1 to enable Perforce-aware write protection. When set, Edit, Write, and NotebookEdit fail with a p4 edit <file> hint if the target file lacks the owner-write bit, which Perforce clears on synced files until p4 edit opens them. This prevents Claude Code from bypassing Perforce change trackingCLAUDE_CODE_PLUGIN_CACHE_DIR
CLAUDE_*
Override the plugins root directory. Despite the name, this sets the parent directory, not the cache itself: marketplaces and the plugin cache live in subdirectories under this path. Defaults to
~/.claude/pluginsCLAUDE_CODE_PLUGIN_DIRS
CLAUDE_*
Plugin directories to load for the session, each loaded the way a
--plugin-dir flag loads it. Separate multiple paths with : on Unix or ; on Windows. Give each path as an absolute path or start it with ~, because Claude Code skips relative paths. Requires Claude Code v2.1.280 or later. See Load a plugin for one sessionCLAUDE_CODE_PLUGIN_DIR_WATCH
CLAUDE_*
Controls whether Claude Code reloads a mod when the mod's files change. Reloading applies to a mod you load from a directory with
--plugin-dir, and it's on by default in interactive sessions. Set to 1 to turn it on in non-interactive sessions as well, or 0 to turn it off in every session. Requires Claude Code v2.1.287 or later. See mod settings and environment variablesTimeout in milliseconds for cloning or refreshing a plugin marketplace (default: 120000). Increase this value for large repositories or slow network connections. See Git clone timed out
Set to
1 to skip the re-clone attempt and keep using the existing marketplace checkout when a marketplace refresh can't reach or authenticate to the remote. Useful in offline or airgapped environments where re-cloning would fail the same way. See Marketplace updates fail in offline environmentsCLAUDE_CODE_PLUGIN_PREFER_HTTPS
CLAUDE_*
Set to
1 to clone GitHub owner/repo shorthand sources over HTTPS instead of SSH. Applies to plugin install and update, and to /plugin marketplace add and update. Useful in CI runners, containers, or any environment without a configured SSH key for github.comCLAUDE_CODE_PLUGIN_SEED_DIR
CLAUDE_*
Path to one or more read-only plugin seed directories, separated by
: on Unix or ; on Windows. Use this to bundle a pre-populated plugins directory into a container image. Claude Code registers marketplaces from these directories at startup and uses pre-cached plugins without re-cloning. See Pre-populate plugins for containersCLAUDE_CODE_POWERSHELL_RESPECT_EXECUTION_POLICY
Shell & Bash
Set to
1 to stop Claude Code from passing -ExecutionPolicy Bypass when spawning PowerShell for tool calls, hooks, and status line commands, and respect the machine's effective execution policy instead. By default Claude Code bypasses execution policy at process scope so .ps1 scripts and module imports work on default-Restricted Windows installs. Process-scope bypass never overrides Group Policy MachinePolicy or UserPolicy regardless of this settingCeiling in milliseconds on idle waiting for background work, such as subagents and workflows, after the final turn in non-interactive mode with the
-p flag. Idle waiting starts over each time Claude takes a turn to handle a background result. Default: 600000, or 10 minutes. When idle waiting reaches the ceiling, Claude Code stops waiting for the remaining background tasks. A running background command that the main conversation started holds the run open past it. Set to 0 to wait indefinitely. Requires Claude Code v2.1.182 or laterCLAUDE_CODE_PROCESS_WRAPPER
CLAUDE_*
Launch the processes Claude Code starts from its own binary, such as the background service that hosts agent view sessions, through a corporate launcher given as an argv prefix like
/opt/corp/launcher. Set it in the env block of user or managed settings, not as a shell export, so the detached background service inherits it; project and local settings can't set it. Equivalent to the processWrapper setting, which requires Claude Code v2.1.210 or later; this variable takes precedence when both are set. The VS Code extension configures its own launcher separately through its claudeProcessWrapper setting. Ignored on Windows. See Run Claude Code behind a corporate launcher for the value format, what the launcher covers, and the contract the launcher must satisfy. Requires Claude Code v2.1.208 or laterCLAUDE_CODE_PROJECT_DIR_NAME
CLAUDE_*
Set together with
CLAUDE_CONFIG_DIR to choose the projects/ directory name Claude Code stores that session's transcripts and auto memory under, in place of one derived from the working directory path. For example, starting Claude Code with CLAUDE_CONFIG_DIR=/srv/tenant-a CLAUDE_CODE_PROJECT_DIR_NAME=work claude stores them under /srv/tenant-a/projects/work/. Claude Code ignores this variable when CLAUDE_CONFIG_DIR is unset, and reads it only from the environment you start claude from, never from a settings file env block. See Name the project directory yourself. Requires Claude Code v2.1.234 or laterCLAUDE_CODE_PROMPT_CACHE_TTL
CLAUDE_*
Set
5m or 1h, the only values Claude Code accepts, to choose the prompt cache TTL for the main conversation: your interactive, -p, and SDK turns, plus the helpers that run inline with them. Takes precedence over the promptCacheTtl setting and over ENABLE_PROMPT_CACHING_1H, and FORCE_PROMPT_CACHING_5M overrides it. The API bills 1-hour cache writes at a higher rate. Requires Claude Code v2.1.242 or laterSet to
1 to propagate W3C trace context when ANTHROPIC_BASE_URL points at a custom proxy. Propagation covers the traceparent header on model and HTTP MCP requests and the TRACEPARENT environment variable for Bash, PowerShell, and hook subprocesses. By default, propagation is enabled only when connected directly to the Anthropic API. Added in v2.1.152. See Traces (beta)Set by host platforms that embed Claude Code and manage model provider routing on its behalf. When set, Claude Code ignores provider-selection, endpoint, and authentication variables such as
CLAUDE_CODE_USE_BEDROCK, ANTHROPIC_BASE_URL, and ANTHROPIC_API_KEY in settings files, so user settings can't override the host's routing. Claude Code also ignores model-selection keys such as model, fallbackModel, and modelOverrides in managed settings, whichever managed source delivers them, so the host's model configuration takes precedence over an out-of-date managed model pin. Claude Code also ignores model-selection variables such as ANTHROPIC_MODEL and the ANTHROPIC_DEFAULT_*_MODEL family in a managed env block; an availableModels allowlist in managed settings still applies unless the host supplies its own. Claude Code also skips the automatic telemetry opt-out it otherwise applies on third-party providers such as Amazon Bedrock, Claude Platform on AWS, Google Cloud's Agent Platform, and Microsoft Foundry, so telemetry follows the standard DISABLE_TELEMETRY opt-out. See Default behaviors by API providerCLAUDE_CODE_PROXY_RESOLVES_HOSTS
Network & proxy
Set to
1 to allow the proxy to perform DNS resolution instead of the caller. Opt-in for environments where the proxy should handle hostname resolutionCLAUDE_CODE_REMOTE
CLAUDE_*
Set automatically to
true when Claude Code is running as a cloud session. Read this from a hook or setup script to detect whether you are in a cloud sessionCLAUDE_CODE_REMOTE_SESSION_ID
CLAUDE_*
Set automatically in cloud sessions to the current session's ID. Read this to construct a link back to the session transcript. See Link output back to the session
CLAUDE_CODE_RESTRICTED
CLAUDE_*
Set to
1 to start the session in restricted mode, the same as passing --restricted. Claude Code ignores this variable in a settings file's env block. Requires Claude Code v2.1.248 or laterSet to
1 to automatically resume if the previous session ended mid-turn. Used in SDK mode so the model continues without requiring the SDK to re-send the prompt. To turn this off, unset the variable or set it to 0. For the VS Code chat panel, see Continue conversations after a reloadMaximum age in milliseconds of the last transcript message for a session that ended mid-turn to continue automatically on resume. When the last message is older than this bound, Claude Code skips the
CLAUDE_CODE_RESUME_INTERRUPTED_TURN automatic resume and its CLAUDE_CODE_RESUME_PROMPT continuation message, and the session starts idle so you continue explicitly. Unset or 0 sets no bound, except that some turns resume only within six hours of their last message, such as one that ended with an API error. A positive value bounds every turn, including those; a negative or non-numeric value applies a one-hour bound. Spawn scripts for long-running agents can set this so a restart against an old transcript doesn't re-run a stale prompt. Claude Code sets a one-hour bound itself when it restarts a crashed agent view session that inherited its conversation from an interactive session. Requires Claude Code v2.1.211 or laterCLAUDE_CODE_RESUME_PROMPT
CLAUDE_*
Override the continuation message Claude Code sends to Claude when
CLAUDE_CODE_RESUME_INTERRUPTED_TURN continues an interrupted turn instead of resending its prompt, or when you resume a deferred tool call with -p. Defaults to Continue from where you left off.. An empty string uses the defaultSet to
1 to keep interrupted tool calls, marked as cut off, in a turn that CLAUDE_CODE_RESUME_INTERRUPTED_TURN continues. When unset, those calls are dropped before the turn continues. Some calls stay dropped, such as calls to subagents, skills, workflows, and tools that wait on a person. For the VS Code chat panel, see Continue conversations after a reload. Requires Claude Code v2.1.309 or laterCLAUDE_CODE_RETRY_WATCHDOG
CLAUDE_*
Set to
1 for unattended sessions such as eval harnesses, CI jobs, or remote workers. Retries 429 and 529 capacity errors indefinitely instead of failing after CLAUDE_CODE_MAX_RETRIES attempts. Claude Code fails at once when a standard-speed request gets a 429 that reports a spend limit or exhausted usage credits, even one from a gateway spend cap that resets on a schedule. Before v2.1.239, the watchdog retried these indefinitely. For fast mode requests, see Handle rate limits. The watchdog backs off up to 5 minutes between attempts, or until the limit resets when the response carries a rate-limit reset time, so a session that hits a usage limit waits out the remaining window. On v2.1.199 or later it also raises the default retry count for other transient errors, such as server errors, timeouts, and dropped connections, to 300, roughly three hours of backoff, and removes the cap of 15 on CLAUDE_CODE_MAX_RETRIES if you set that variable explicitly. Requires Claude Code v2.1.186 or laterMaximum time in milliseconds that each API request spends waiting out
429 and 529 errors when CLAUDE_CODE_RETRY_WATCHDOG is set. Once that time is spent, the next such error ends the request. Give a positive whole number in plain digits, such as 1800000 for 30 minutes. When unset, the wait has no limit. Requires Claude Code v2.1.295 or laterMinimum interval in milliseconds between checks of whether a usage limit was already lifted, while a request waits for that limit to reset with
CLAUDE_CODE_RETRY_WATCHDOG set. When a check finds the limit lifted, the request goes out at once. Give a whole number in plain digits from 60000, one minute, to 10800000, three hours. Checks are made only for a claude.ai subscription's session or weekly limit while usage credits aren't in use, and not while CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC is set. When this variable is unset or its value is outside that range, no checks are made. Requires Claude Code v2.1.305 or laterCLAUDE_CODE_SAFE_MODE
CLAUDE_*
Set to
1 to start in safe mode: CLAUDE.md, skills, plugins, hooks, MCP servers, custom commands and agents, output styles, workflows, custom themes, custom keybindings, status line and file-suggestion commands, LSP servers, and auto memory do not load, for troubleshooting a broken configuration. Managed settings policy still applies, including policy-configured hooks, status line, and file-suggestion commands; managed plugins, managed skills, managed CLAUDE.md, and policy-configured MCP servers do not. Equivalent to passing --safe-mode. Directly spawned child processes inherit the variableCLAUDE_CODE_SCRIPT_CAPS
CLAUDE_*
JSON object limiting how many times specific scripts may be invoked per session when
CLAUDE_CODE_SUBPROCESS_ENV_SCRUB is set. Keys are substrings matched against the command text; values are integer call limits. For example, {"deploy.sh": 2} allows deploy.sh to be called at most twice. Matching is substring-based so shell-expansion tricks like ./scripts/deploy.sh $(evil) still count against the cap. Runtime fan-out via xargs or find -exec is not detected; this is a defense-in-depth controlCLAUDE_CODE_SCROLL_SPEED
CLAUDE_*
Set the mouse wheel scroll multiplier in fullscreen rendering. Accepts any positive value up to 20, including fractional values below 1 such as
0.5 to slow accelerated trackpad and wheel scrolling in terminals that already amplify wheel events. Set to 3 to match vim if your terminal sends one wheel event per notch without amplification. Ignored in the JetBrains IDE terminal, where Claude Code uses its own scroll handlingCLAUDE_CODE_SEND_FEEDBACK
CLAUDE_*
Set to
0 to turn off Claude-drafted feedback for a session. Set to 1 to turn it on where your account already has access; the variable can't grant access itself, and the other switches that turn feedback off, such as DISABLE_FEEDBACK_COMMAND and the feedbackDrafts setting's off value, still applyOverride the time budget in milliseconds for SessionEnd hooks. The value is also the timeout for each hook that sets no
timeout of its own. Applies to session exit, /clear, and switching sessions via interactive /resume. By default the budget is 1.5 seconds, automatically raised to the highest per-hook timeout configured in settings files, up to 60 seconds. Timeouts on plugin-provided hooks do not raise the budgetCLAUDE_CODE_SESSION_ID
CLAUDE_*
Set automatically to the current session ID in Bash and PowerShell tool subprocesses, hook command subprocesses, and stdio MCP server subprocesses. For Bash, PowerShell, and hooks this matches the
session_id field in the hook JSON input and is updated on /clear. An MCP server subprocess retains the ID it was spawned with. On --resume <session-id> it receives the resumed ID, matching hooks and Bash. On --continue or --resume without an explicit ID it may receive the initial startup ID instead. Use to correlate scripts and external tools with the Claude Code session that launched themCLAUDE_CODE_SHELL
Shell & Bash
Set the shell Claude Code uses to run Bash tool commands. Accepts a path to a
bash or zsh binary, for example /opt/homebrew/bin/bash. Other shells such as fish are not supported. If the value is not a working bash or zsh path, Claude Code ignores it and falls back to auto-detection. Auto-detection uses your $SHELL when it points to bash or zsh, otherwise it picks the first working zsh then bash found on your PATH and standard install locationsCLAUDE_CODE_SHELL_PREFIX
Shell & Bash
Command prefix that wraps shell commands Claude Code spawns: Bash tool calls, hook commands, status line commands, and stdio MCP server startup commands. PowerShell hooks and exec-form hooks run without the prefix. Useful for logging or auditing. Setting a bare executable path such as
/path/to/logger.sh runs each command as /path/to/logger.sh '<command>'. The wrapper receives the command line as a single shell-quoted argument in $1, so the wrapper must re-evaluate $1 with a shell, for example exec bash -c "$1". Treating $1 as a bare executable path breaks stdio MCP servers that pass arguments such as npx -y <package>. For Bash tool calls, $1 contains the full shell invocation Claude Code assembles, including environment setup, not only the command Claude ranCLAUDE_CODE_SIMPLE
CLAUDE_*
Set to
1 to run with a minimal system prompt and only the Bash, file read, and file edit tools. MCP tools from --mcp-config are still available. Disables auto-discovery of hooks, skills, custom commands, subagents, installed plugins, MCP servers, auto memory, and CLAUDE.md. Skills in a directory you pass with --add-dir still load. OAuth tokens and keychain credentials are not read, so Anthropic authentication must come from ANTHROPIC_API_KEY or an apiKeyHelper in --settings. Equivalent to passing --bareCLAUDE_CODE_SIMPLE_SYSTEM_PROMPT
CLAUDE_*
Choose between Claude Code's full system prompt and a shorter one with abbreviated tool descriptions. When unset, Haiku 4.5, Sonnet 5, Opus 4.7, and earlier models in those families use the full prompt by default, and newer models use the shorter one. Set to
1 to use the shorter prompt on any model. Set to 0, false, no, or off to use the full prompt on any model, even where an experiment or server configuration would otherwise select the shorter one. Either prompt keeps the full tool set, hooks, MCP servers, and CLAUDE.md discoveryCLAUDE_CODE_SKIP_ANTHROPIC_AWS_AUTH
Cloud providers
Skip client-side authentication for Claude Platform on AWS, for gateways that sign requests themselves
CLAUDE_CODE_SKIP_AWS_CRED_CACHE
Cloud providers
Set to
1 to turn off the in-process cache of credentials resolved from the AWS default credential provider chain, so Claude Code resolves the chain on every API request. With the cache off, an SSO-backed profile requests credentials from IAM Identity Center on every request. See credential caching and resolution timeout. Requires Claude Code v2.1.207 or laterCLAUDE_CODE_SKIP_BEDROCK_AUTH
Cloud providers
Skip AWS authentication for Amazon Bedrock (for example, when using an LLM gateway)
Set to
1 to treat a failed fast mode availability check as available, for networks that block the check's direct request to api.anthropic.com. Claude Code still honors a "disabled by your organization" responseSet to
1 to skip the client-side fast mode availability check, for proxies that intercept the check's request rather than refuse it. The API still rejects fast mode requests when your organization has fast mode disabledCLAUDE_CODE_SKIP_FOUNDRY_AUTH
Cloud providers
Skip Azure authentication for Microsoft Foundry, for a proxy or gateway that injects its own
Authorization header. Claude Code sends requests without an Azure credential and preserves the Authorization header you supply, for example through ANTHROPIC_CUSTOM_HEADERS. Ignored when ANTHROPIC_FOUNDRY_API_KEY or ANTHROPIC_FOUNDRY_AUTH_TOKEN is set. Before v2.1.203, this variable left the Microsoft Foundry client unable to send requests unless an API key was also setCLAUDE_CODE_SKIP_MANTLE_AUTH
CLAUDE_*
Skip AWS authentication for Amazon Bedrock Mantle (for example, when using an LLM gateway)
The startup model checks on Amazon Bedrock and Google Cloud's Agent Platform remember on this machine which models they found your account can't invoke, for up to a day. Set to
1 to turn that memory off. Requires Claude Code v2.1.285 or laterCLAUDE_CODE_SKIP_PROMPT_HISTORY
CLAUDE_*
Set to
1 to skip writing prompt history and session transcripts to disk. Sessions started with this variable set do not appear in --resume, --continue, or up-arrow history. Useful for ephemeral scripted sessionsCLAUDE_CODE_SKIP_VERTEX_AUTH
Cloud providers
Skip Google authentication for Google Cloud's Agent Platform (for example, when using an LLM gateway)
Set to
1 to have a session started with --output-format stream-json write a result message naming why Claude Code refused to start for startup failures that otherwise end with stderr alone. Requires Claude Code v2.1.274 or laterCLAUDE_CODE_STOP_HOOK_BLOCK_CAP
CLAUDE_*
Maximum number of consecutive times a Stop or SubagentStop hook may block the turn from ending before Claude Code overrides it and ends the turn anyway (default: 8). Set to
0 to disable the cap. Raise this if your hook legitimately needs more iterations to resolveCLAUDE_CODE_SUBAGENT_MODEL
CLAUDE_*
The default model for subagents, agent team teammates, and workflow agents that aren't assigned a model another way. Accepts an alias such as
haiku or a full model name. Two sources take precedence over it: a model Claude passes when it spawns the agent, and a model field in the agent's definition, including inherit. To change that, set CLAUDE_CODE_SUBAGENT_MODEL_FORCE. See Choose a model for the full order. Setting it to inherit is the same as leaving it unset. Before v2.1.251, this variable overrode both the per-invocation model and the definition's model fieldCLAUDE_CODE_SUBAGENT_MODEL_FORCE
CLAUDE_*
Set to
1 to force one model onto subagents, teammates, and workflow agents. Run every subagent on one model says which model that is. Requires Claude Code v2.1.257 or laterSet
5m or 1h, the only values Claude Code accepts, to choose the prompt cache TTL for requests outside the main conversation, such as subagents, workflows, and background work. Takes precedence over the subagentPromptCacheTtl setting and over ENABLE_PROMPT_CACHING_1H, and FORCE_PROMPT_CACHING_5M overrides it. The API bills 1-hour cache writes at a higher rate. Requires Claude Code v2.1.242 or laterCLAUDE_CODE_SUBPROCESS_ENV_SCRUB
CLAUDE_*
Set to
1 to strip credentials from the environments of the subprocesses Claude Code starts, such as Bash commands, hooks, and stdio MCP servers. The scrub recognizes a credential by its variable name or its value, and it leaves GitHub tokens and proxy settings in place. See What the subprocess environment scrub removes. claude-code-action sets this automatically when allowed_non_write_users is configuredCLAUDE_CODE_SYNC_PLUGIN_INSTALL
CLAUDE_*
Set to
1 in non-interactive mode (the -p flag) to wait for plugin installation to complete before the first query. Without this, plugins install in the background and may not be available on the first turn. Combine with CLAUDE_CODE_SYNC_PLUGIN_INSTALL_TIMEOUT_MS to bound the waitTimeout in milliseconds for synchronous plugin installation. When exceeded, Claude Code proceeds without plugins and logs an error. No default: without this variable, synchronous installation waits until complete
CLAUDE_CODE_SYNC_SKILLS
CLAUDE_*
Set to
1 in non-interactive mode with the -p flag to make Claude Code download the skills enabled for your claude.ai account in that run and wait for the list of them, up to CLAUDE_CODE_SYNC_SKILLS_WAIT_TIMEOUT_MS, before it runs the first query. Requires claude.ai authentication. Terminal sessions where you sign in with your claude.ai account sync these skills without this variable, so set it only when a -p run needs your current skills on its first queryTimeout in milliseconds for the skills resync that runs mid-session when an app built on the Agent SDK reloads skills (default: 30000). When exceeded, the reload continues with whichever skills have arrived, and the remaining downloads finish in the background
Timeout in milliseconds for the first query to wait for the initial skill list when
CLAUDE_CODE_SYNC_SKILLS is set (default: 5000). When exceeded, the first query runs with whichever skills have arrived. The downloads finish in the background either way, and Claude waits for a skill's download when it invokes that skillCLAUDE_CODE_SYNTAX_HIGHLIGHT
CLAUDE_*
Set to
false to disable syntax highlighting in diff output. Useful when colors interfere with your terminal setup. To also disable highlighting in code blocks and file previews, use the syntaxHighlightingDisabled settingCLAUDE_CODE_TASK_LIST_ID
CLAUDE_*
Share a task list across sessions. Set the same ID in multiple Claude Code instances to coordinate on a shared task list, in sessions that have the Task tools. See Task list
CLAUDE_CODE_TMPDIR
CLAUDE_*
Override the temp directory used for internal temp files. Claude Code appends
/claude-{uid}/ to this path on Unix, or /claude/ on Windows. Default: /tmp on macOS, os.tmpdir() on Linux and Windows. On macOS and Linux, sandboxed Bash subprocesses receive a short fallback $TMPDIR under the system default when your override is a long path, since some tools fail when temp paths get too long. Unsandboxed Bash commands inherit your shell's $TMPDIR when it is set. On native Windows, when your shell doesn't set $TMPDIR, a Bash command that references $TMPDIR receives your override, or %TEMP% when you haven't set one. Claude Code's own temp files always use your override. Set it in your shell, user settings, or managed settings. Ignored in project and local settingsCLAUDE_CODE_TMUX_TRUECOLOR
CLAUDE_*
Set to any non-empty value, such as
1, to allow 24-bit truecolor output inside tmux. Setting it to `0` or `false` still allows truecolor, unlike most on/off variables; unset the variable to restore the 256-color clamp. By default, Claude Code clamps to 256 colors when $TMUX is set because tmux does not pass through truecolor escape sequences unless configured to. Set this after adding set -ga terminal-overrides ',*:Tc' to your ~/.tmux.conf. See Terminal configuration for other tmux settingsOn Linux and WSL, set to a comma-separated list of the kinds of processes Claude Code excludes from the tool memory cap, such as
mcp or lsp. Set none to cap every kind, or all-new to cap only Bash, PowerShell, and Monitor tool commands. Claude Code keeps Bash, PowerShell, and Monitor tool commands under the cap whatever you list. Requires Claude Code v2.1.246 or laterCLAUDE_CODE_TOOL_MEMORY_LIMIT
CLAUDE_*
On Linux and WSL, set to a size such as
4G to cap the memory that Bash and PowerShell tool commands can use, and Monitor tool commands on v2.1.246 or later. Write the size in plain digits, alone for a number of bytes or with a K, M, G, or T suffix. Set 0 or off to turn the cap off. Once the first process Claude Code starts has turned the cap on or off, a changed value takes effect the next time you launch claude. Requires Claude Code v2.1.233 or laterCLAUDE_CODE_TRANSCRIPT_LOCAL_GC
CLAUDE_*
Set to
1 to limit how large the transcript file of a long -p or Agent SDK session grows. After each compaction, once the file is larger than 5 MB, Claude Code removes the history from before that compaction. On v2.1.296 or later, the file stays as it is when removing that history would shrink it by less than 10%. Resuming the session restores the same conversation whether or not the file was trimmed. Set it in the environment you start Claude Code from, since a settings env block can't turn it on. Requires Claude Code v2.1.287 or laterDeadline in milliseconds before Claude Code cancels a dialog it forwards to a remote client such as a Remote Control or SDK host, or the approval dialog for a held cross-session message; permission prompts and
AskUserQuestion questions use their own flows and aren't governed by it. On Claude Code v2.1.236 or later, it also bounds the mid-session Fable usage-credits consent prompt in a session that may be running unattended. Control inbound messages and non-interactive sessions cover the full held-message expiry rules, including the cases where the deadline doesn't apply. Overrides the dialogExpiry setting. 0 or a negative value disables the deadline. Ignored in project and local settingsCLAUDE_CODE_USE_ANTHROPIC_AWS
Cloud providers
CLAUDE_CODE_USE_BEDROCK
Cloud providers
Use Amazon Bedrock
CLAUDE_CODE_USE_FOUNDRY
Cloud providers
CLAUDE_CODE_USE_MANTLE
Cloud providers
Use the Amazon Bedrock Mantle endpoint
CLAUDE_CODE_USE_POWERSHELL_TOOL
Cloud providers
Controls the PowerShell tool. On Windows without Git Bash, the tool is enabled automatically; set to
0 to disable it. On Windows with Git Bash installed, the tool is on by default for claude.ai and Console accounts; set to 1 to enable it in Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry sessions, or 0 to turn it off. On Linux, macOS, and WSL, set to 1 to enable it, which requires pwsh on your PATH. When enabled on Windows, Claude can run PowerShell commands natively instead of routing through Git Bash. See PowerShell toolCLAUDE_CODE_USE_VERTEX
Cloud providers
CLAUDE_CODE_WARN_DISK_FREE_GIB
CLAUDE_*
Set to a whole number of GiB, such as
10, to have Claude Code warn Claude when free space on the working directory's filesystem falls below that amount. The warning is a system reminder saying how much is free. The reminder is off when the variable is unset, 0, or not plain digits. Set it in the environment that launches Claude Code, since Claude Code ignores a copy delivered through a settings env block. Requires Claude Code v2.1.304 or laterCLAUDE_CODE_WARN_MEMORY_FREE_GIB
CLAUDE_*
On Linux and WSL, set to a whole number of GiB such as
4 to have Claude Code warn Claude when available memory falls below that amount. The warning is a system reminder saying how much is available. The reminder is off when the variable is unset, 0, or not plain digits. Set it in the environment that launches Claude Code, since Claude Code ignores a copy delivered through a settings env block. Requires Claude Code v2.1.304 or laterSet to the number of milliseconds WebFetch keeps each fetched URL's response cached. The default is
900000, which is 15 minutes. Takes plain digits only; 0, a decimal, or any other spelling keeps the default. Claude Code reads the value once per launch, so a change in a settings env block applies when you next launch claude. Requires Claude Code v2.1.233 or laterCLAUDE_CODE_WEBFETCH_DEADLINE_MS
CLAUDE_*
Upper bound in milliseconds on how long WebFetch waits for a page to download, including any redirects it follows. A download that hasn't completed by then fails with a deadline error. The default is
300000, which is five minutes. Set to 0 to remove the limit. Takes plain digits only; a decimal or any other spelling keeps the default. Requires Claude Code v2.1.268 or laterRate at which a session's WebSearch limit refills, in calls per hour. The default is
100 in an interactive terminal session. In a non-interactive session the default is 0, which turns refill off. Takes plain digits only; any other spelling reads as unset. Requires Claude Code v2.1.290 or laterWhen
CLAUDE_AUTO_BACKGROUND_TASKS is set to 1, how long Claude Code waits before each reminder to Claude to check on background subagents that are still running. Takes one or more comma-separated waits in whole seconds from 1 to 86400, such as 600 or 600,1800,3600. Each value is the wait before the next reminder, and the last value repeats. Takes plain digits only; any other value or spelling reads as unset. When unset, there are no reminders. Requires Claude Code v2.1.283 or laterHow many agents a single workflow run executes at once, from
1 to 256. By default, a run executes up to 16 agents at once, fewer when Claude Code has fewer CPUs available; queued agent() calls wait for a free slot. Each running agent's transcript stays in Claude Code's memory, so higher values raise memory use. Takes plain digits only; out-of-range values and other spellings keep the default. Requires Claude Code v2.1.269 or laterUpper bound in milliseconds on how long a workflow agent waits for a same-prefix sibling's first response to begin before sending its own first request. When a fan-out starts several agents that share a prompt-cache prefix, Claude Code holds all but the first agent for up to this long so the rest read the cached prefix instead of each processing it uncached. Default
5000. Set to 0 to disable the wait. When DISABLE_PROMPT_CACHING is set, agents never wait. Requires Claude Code v2.1.229 or laterSet to
1 to show, above the prompt, a line for each of the last three checks the You should know mod made in this session. Use it to confirm the mod is checking when no notes appear. Requires Claude Code v2.1.287 or laterCLAUDE_CONFIG_DIR
CLAUDE_*
Override the configuration directory (default:
~/.claude). All settings, session history, and plugins are stored under this path. For credentials, see where Claude Code stores credentials. Useful for running multiple accounts side by side: for example, alias claude-work='CLAUDE_CONFIG_DIR=~/.claude-work claude'. Set it in your shell, user settings, or managed settings. In a settings file, write the absolute path. Ignored in project and local settingsCLAUDE_EFFORT
CLAUDE_*
Set automatically in Bash tool subprocesses and hook commands to the effort level setting when the subprocess starts:
low, medium, high, xhigh, or max. Matches the effort.level field passed to hooks. Only set when the current model supports the effort parameterCLAUDE_ENABLE_BYTE_WATCHDOG
CLAUDE_*
Set to
1 to force-enable the byte-level streaming idle watchdog, or set to 0 to force-disable it. 0 also turns off the first-byte deadline on the connections where that deadline runs. When unset, the watchdog is enabled by default for direct Anthropic API and Claude Platform on AWS connections, and for streaming responses on gateway connections reached through ANTHROPIC_BASE_URL or ANTHROPIC_AWS_BASE_URL; before v2.1.222 it didn't run on those gateway connections, so the event-level watchdog could report a stall there even while keep-alive pings were arriving. For timeouts and how the timers interact, see Streaming idle watchdogsCLAUDE_ENABLE_BYTE_WATCHDOG_BEDROCK
Cloud providers
Set to
1 to enable the byte-level streaming idle watchdog on Amazon Bedrock vnd.amazon.eventstream responses, which also enables the first-byte deadline on Bedrock streaming requests. Off by default. Configure the timeout with CLAUDE_STREAM_IDLE_TIMEOUT_MSCLAUDE_ENABLE_STREAM_WATCHDOG
CLAUDE_*
Set to
0 to force-disable the event-level streaming idle watchdog, or set to 1 to force-enable it. When unset, the watchdog is on by default for all providers. Before v2.1.196, the unset default was server-controlled on the direct Anthropic API and off on other providers. Configure the timeout with CLAUDE_STREAM_IDLE_TIMEOUT_MS; for the other stall timers that run alongside this one, see Streaming idle watchdogsCLAUDE_ENV_FILE
CLAUDE_*
Path to a shell script whose contents Claude Code runs before each Bash command in the same shell process, so exports in the file are visible to the command. Use to persist virtualenv or conda activation across commands. PowerShell commands receive its variables too, in v2.1.296 or later, under the conditions in Persisted variables in PowerShell commands. Also populated dynamically by SessionStart, Setup, CwdChanged, and FileChanged hooks
CLAUDE_JOB_DIR
CLAUDE_*
Set by Claude Code in each background session to that session's
~/.claude/jobs/<id> directory. Shell commands that the session runs inherit it. Write scratch files to $CLAUDE_JOB_DIR/tmp. Claude's Write and Edit calls there don't prompt for permission, and the directory is removed when the session is deletedCLAUDE_PID
CLAUDE_*
Claude Code sets this to its own process ID in the subprocesses it spawns: Bash and PowerShell tool commands and hook commands. On Linux, the Bash tool's shell integration uses it to refuse a
pkill pattern that would match the Claude Code process itself; see the error reference. Read it from your own scripts to identify or signal the parent Claude Code process deliberately. Requires Claude Code v2.1.214 or laterPrefix for auto-generated Remote Control session names when no explicit name is provided. Defaults to your machine's hostname, producing names like
myhost-graceful-unicorn. The --remote-control-session-name-prefix CLI flag sets the same value for a single invocationDeadline in milliseconds for the first response byte of a streaming request, on the connections where the first-byte deadline runs. For how Claude Code clamps it, the extra time it adds for large request bodies, and how it picks the deadline when you leave this unset, see No response from API. Requires Claude Code v2.1.242 or later
CLAUDE_STREAM_IDLE_TIMEOUT_MS
CLAUDE_*
Timeout in milliseconds before the event- and byte-level streaming idle watchdogs close a stalled connection. When you set this variable explicitly, the minimum is
300000 (5 minutes); lower values are silently clamped to absorb extended thinking pauses and proxy buffering, and the byte-level watchdog caps the value at 30 minutes. CLAUDE_BYTE_STREAM_IDLE_TIMEOUT_MS takes precedence over this variable for the byte-level watchdog. For the per-watchdog unset defaults, see Streaming idle watchdogsCLAUDE_SUBAGENT_BG_SHELL_MAX_MS
Shell & Bash
Removed in v2.1.260 and now a no-op. Previously capped how long a background shell command that a subagent started could run, in milliseconds, with a 60-minute default. See the background command lifetime rules
DEBUG
Other
Set to
1 to enable debug mode, equivalent to launching with --debug. Debug logs are written to ~/.claude/debug/<session-id>.txt, or to the path set by CLAUDE_CODE_DEBUG_LOGS_DIR. Only the truthy values 1, true, yes, and on enable debug mode, so namespace patterns like DEBUG=express:* set for other tools do not trigger itDISABLE_AUTOUPDATER
Disable features
Set to
1 to disable automatic background updates. Manual claude update still works. Use DISABLE_UPDATES to block bothDISABLE_AUTO_COMPACT
Disable features
Set to
1 to disable automatic compaction when approaching the context limit, along with idle compaction. The manual /compact command remains available. Use when you want explicit control over when compaction occurs. Overrides the autoCompactEnabled settingDISABLE_COMPACT
Disable features
Set to
1 to disable all compaction: both automatic compaction and the manual /compact commandDISABLE_COST_WARNINGS
Disable features
Set to
1 to disable cost warning messagesDISABLE_DOCTOR_COMMAND
Disable features
Set to
1 to hide the /doctor setup checkup skill and its /checkup alias. Useful for managed deployments where users shouldn't run setup diagnostics from a session. Doesn't affect the claude doctor terminal command. Before v2.1.205, this variable hid the /doctor diagnostics screen commandDISABLE_ERROR_REPORTING
Disable features
Set to any non-empty value, such as
1, to opt out of error reporting. Setting it to `0` or `false` still opts out, unlike most on/off variables; unset the variable to turn error reporting back onDISABLE_EXTRA_USAGE_COMMAND
Disable features
Set to
1 to hide the /usage-credits command that lets users purchase additional usage beyond rate limitsDISABLE_FEEDBACK_COMMAND
Disable features
Set to
1 to disable the /feedback command and Claude-drafted feedback. Also disables /bug and /share, which report through the same path; before v2.1.212 they were aliases of /feedback, so the command was disabled under every name. The older name DISABLE_BUG_COMMAND is also acceptedDISABLE_GROWTHBOOK
Disable features
Set to
1 or true to disable feature-flag fetching and use code defaults for every flag. This makes Remote Control and the other features that need feature-flag fetching unavailable. Setting it to 0 or false leaves fetching on. Telemetry event logging stays on unless DISABLE_TELEMETRY is also setDISABLE_INSTALLATION_CHECKS
Disable features
Set to
1 to disable installation warnings. Use only when manually managing the installation location, as this can mask issues with standard installationsDISABLE_INSTALL_GITHUB_APP_COMMAND
Disable features
Set to
1 to hide the /install-github-app command. Already hidden when using third-party providers (Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry)DISABLE_INTERLEAVED_THINKING
Disable features
Set to
1 to prevent sending the interleaved-thinking beta header. Useful when your LLM gateway or provider does not support interleaved thinkingDISABLE_LOGIN_COMMAND
Disable features
Set to
1 to hide the /login command. Useful when authentication is handled externally via API keys or apiKeyHelperDISABLE_LOGOUT_COMMAND
Disable features
Set to
1 to hide the /logout commandDISABLE_PROMPT_CACHING
Disable features
Set to
1 to disable prompt caching for all models (takes precedence over per-model settings)DISABLE_PROMPT_CACHING_FABLE
Disable features
Set to
1 to disable prompt caching for Fable modelsDISABLE_PROMPT_CACHING_HAIKU
Disable features
Set to
1 to disable prompt caching for the default Haiku model, wherever it runsDISABLE_PROMPT_CACHING_OPUS
Disable features
Set to
1 to disable prompt caching for the default Opus modelDISABLE_PROMPT_CACHING_SONNET
Disable features
Set to
1 to disable prompt caching for the default Sonnet modelDISABLE_TELEMETRY
Telemetry
Set to any non-empty value, such as
1, to opt out of telemetry. Setting it to `0` or `false` still opts out, unlike most on/off variables; unset the variable to turn telemetry back on. Telemetry events don't include user data like code, file paths, or Bash commands. Also disables feature-flag fetching. See Turn telemetry off for your organizationDISABLE_UPDATES
Disable features
Set to
1 to block all updates including manual claude update and claude install. Stricter than DISABLE_AUTOUPDATER. Use when distributing Claude Code through your own channels and users should not self-updateDISABLE_UPGRADE_COMMAND
Disable features
Set to
1 to hide the /upgrade commandDO_NOT_TRACK
Other
Set to
1 to opt out of telemetry, with the same effect as DISABLE_TELEMETRY, including on feature-flag fetching. Claude Code reads this variable as a standard boolean, so 0 leaves telemetry on, and honors it as the cross-tool convention recognized by many developer CLIsSet to
1, and set BETA_TRACING_ENDPOINT to your OTLP/HTTP collector endpoint, to turn on detailed beta tracing, which adds content-bearing span attributes and the claude_code.hook span. Interactive CLI sessions also require your organization to be allowlisted for the beta. Both variables are ignored in project and local settingsSet to
false to stop Claude Code from fetching claude.ai MCP servers. Enabled by default for logged-in users. To disable per-project or per-org, set disableClaudeAiConnectors in settings insteadSet to
1 to request a 1-hour prompt cache TTL instead of the default 5 minutes. Intended for API key, Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry, and Claude Platform on AWS users. For subscription users within included usage, Claude Code requests the 1-hour TTL automatically on the main conversation. Subscription users drawing on usage credits can set it to keep the 1-hour TTL. 1-hour cache writes are billed at a higher rate. To choose the TTL separately for the main conversation and for requests outside it, use CLAUDE_CODE_PROMPT_CACHE_TTL and CLAUDE_CODE_SUBAGENT_PROMPT_CACHE_TTL, which take precedence over this variableENABLE_PROMPT_CACHING_1H_BEDROCK
Cloud providers
Deprecated. Use
ENABLE_PROMPT_CACHING_1H instead. Has no effect on Claude apps gateway sessions, even when the gateway routes to Amazon BedrockENABLE_TOOL_SEARCH
Other
Controls MCP tool search. Unset or
true defers MCP tools, except in the cases that keep tool search off. auto turns tool search on once definitions reach 10% of the context window. auto:N sets a custom threshold, such as auto:5 for 5%. false loads all tools upfront. If a gateway rejects tool search, see Tool search through an LLM gatewaySet to
1 to force plugin auto-updates even when the main auto-updater is disabled via DISABLE_AUTOUPDATERFORCE_HYPERLINK
Other
Set to
1 to enable clickable OSC 8 hyperlinks when your terminal supports them but isn't auto-detected. When unset, Claude Code enables most hyperlinks only when it detects terminal support. The footer PR or merge request badge and long sign-in URLs are links either way. Set 0, false, no, or off to render all of them as plain text. Before v2.1.314, false, no, and off enabled hyperlinks insteadSet to
1 to force the 5-minute prompt cache TTL even when 1-hour TTL would otherwise apply. Overrides CLAUDE_CODE_PROMPT_CACHE_TTL, CLAUDE_CODE_SUBAGENT_PROMPT_CACHE_TTL, ENABLE_PROMPT_CACHING_1H, and the promptCacheTtl and subagentPromptCacheTtl settingsHTTP_PROXY
Network & proxy
Specify HTTP proxy server for network connections
HTTPS_PROXY
Network & proxy
Specify HTTPS proxy server for network connections
IS_DEMO
Other
Set to any non-empty value, such as
1, to enable demo mode: hides your email and organization name from the header and /status output, and skips onboarding. Setting it to `0` or `false` still enables demo mode, unlike most on/off variables; unset the variable to turn it off. Useful when streaming or recording a sessionMaximum number of tokens allowed in MCP tool responses (default: 25000). Claude Code displays a warning when output exceeds 10,000 tokens. Tools that declare
anthropic/maxResultSizeChars use that character limit for text content instead, but image content from those tools is still subject to this variable. A successful text result longer than 50,000 characters from a tool without that annotation is saved to a file regardless of this variableNumber of attempts Claude Code allows when the model's response fails validation against the
--json-schema in non-interactive mode with the -p flag; after that many failed attempts with no valid output, the run fails. The same cap applies when a workflow subagent's structured output fails validation. Defaults to 5, a first attempt plus four retriesMAX_THINKING_TOKENS
Other
Fixed token budget for extended thinking. Claude Code caps it at one token below the request's max output tokens and never below 1,024. See
CLAUDE_CODE_MAX_OUTPUT_TOKENS for how that limit is set. When unset and thinking is enabled, models with adaptive reasoning choose their own thinking depth, and other models use the cap. Set to 0 to disable thinking on the Anthropic API, except on Opus 5.5, Sonnet 5.5, Haiku 5.5, and the Fable models, which can't have thinking turned off. On third-party providers, 0 omits the thinking parameter instead. With thinking turned off on the Anthropic API, Claude Code sends effort high instead of a higher level to models it knows don't accept that combination, such as Opus 5. For a positive value, Claude Code ignores the number itself on adaptive reasoning models, except when CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING turns adaptive reasoning offOAuth client secret for MCP servers that require pre-configured credentials. Avoids the interactive prompt when adding a server with
--client-secretControls whether startup waits for MCP servers to connect before the first query. MCP startup is non-blocking by default: servers connect in the background and their tools become available as they finish. Set to
0 to make Claude Code wait for servers to connect before the first query. Servers configured with alwaysLoad: true still make startup wait regardless, except when served from the discovery cache, since their tools must be present when the first prompt is built. In non-interactive mode (-p) without --input-format stream-json, Claude Code also waits for still-pending servers before the first turn regardless of this variable. When you pass --mcp-config explicitly, the wait has a longer deadline; see that flag's entry for the cached-server exceptionHow long blocking MCP startup waits, in milliseconds, for the connection batch before snapshotting the tool list (default: 5000). Applies when
MCP_CONNECTION_NONBLOCKING=0 or for servers marked alwaysLoad: true. Servers still pending at the deadline keep connecting in the background. Distinct from MCP_TIMEOUT, which bounds an individual server's connect attemptTurns the MCP discovery cache on or off. With the cache on, a remote HTTP or SSE server you've used before can show the
cached status, and Claude Code connects it on its first tool call instead of at startup. The cache is off by default unless a gradual rollout has enabled it for your account. Set to 1 to turn it on, or 0 to keep it off even when the rollout has enabled it. Before v2.1.238, the cache was on by default. The cached status requires Claude Code v2.1.221 or laterMaximum age, in seconds, of a discovery-cache entry (default: 14400, or 4 hours). At a start where the entry is older than that, Claude Code discards it and connects the server at startup, as it does with the cache off. Claude Code caps the value at 7 days. Before v2.1.238, the default was 86400, or 24 hours, and Claude Code didn't cap the value
At a start where a discovery-cache entry is older than
MCP_DISCOVERY_CACHE_TTL_S, Claude Code refreshes it in the background. This variable sets how many refreshes in a row can fail before Claude Code discards the entry and connects the server at the next start instead (default: 1). Raise it if your network connection drops occasionally, so that one failed refresh doesn't discard the entry. Requires Claude Code v2.1.238 or laterSeconds for which Claude Code uses a discovery-cache entry without refreshing it (default: 900). At a start where the entry is older than that, Claude Code still uses it but refreshes it in the background. Once the entry is older than
MCP_DISCOVERY_CACHE_MAX_STALE_S, Claude Code discards it instead. Claude Code caps the value at MCP_DISCOVERY_CACHE_MAX_STALE_S, which is 4 hours by default. Before v2.1.238, Claude Code didn't cap the valueFixed port for the OAuth redirect callback, as an alternative to
--callback-port when adding an MCP server with pre-configured credentialsOn the v2 MCP client runtime only, controls whether Claude Code probes servers for MCP protocol revision 2026-07-28. Set
legacy to skip the probe, so that every server connects with the handshake from before that revision. Set auto to probe the server kinds that support the probe: HTTP and stdio servers, claude.ai connectors, and the connectors of cloud and Remote Control sessions. With the variable unset, Claude Code probes those same kinds by default; see MCP client runtimes. Any other value is ignored with a warning in the debug log. Requires Claude Code v2.1.221 or laterMaximum number of remote MCP servers (HTTP/SSE) to connect in parallel during startup (default: 20)
Pin which MCP client runtime this process connects to MCP servers with:
v1, built on MCP TypeScript SDK 1.x, or v2, built on MCP TypeScript SDK 2.0. Without the variable, Claude Code uses v2, starting with the versions listed in that section. On Claude Code v2.1.221 or later, the v2 runtime checks the issuer an MCP OAuth server returns in its authorization response and fails the sign-in with an error that begins Issuer mismatch in authorization response when it doesn't match. The v1 runtime doesn't run this check. If you set an unrecognized value, Claude Code ignores it and writes a warning to the debug log. Claude Code reads the value once per process. Requires Claude Code v2.1.218 or laterMaximum number of local MCP servers (stdio) to connect in parallel during startup (default: 3)
MCP_TIMEOUT
MCP
Timeout in milliseconds for MCP server startup (default: 30000, or 30 seconds)
Timeout in milliseconds for MCP tool execution (default: 100000000, about 28 hours). For an HTTP, SSE, or claude.ai connector server, each request also times out after 60 seconds by default; set this variable, or the per-server
timeout, above 60000 to raise that per-request limit. A lower value still shortens the overall tool-execution timeout but leaves the per-request limit at 60 seconds. Stdio and WebSocket servers have no per-request timer. A per-server timeout field in .mcp.json overrides this for that server. A per-server timeout of at least 1000 also sets the minimum idle window for that server's tool calls, so CLAUDE_CODE_MCP_TOOL_IDLE_TIMEOUT never aborts them sooner; this floor requires Claude Code v2.1.203 or later. For the env variable, values below 1000 are floored to one second; for the per-server field, values below 1000 are ignoredNO_PROXY
Network & proxy
List of domains and IPs to which requests will be directly issued, bypassing proxy
OTEL_ATTRIBUTE_VALUE_LENGTH_LIMIT
Telemetry
Standard OpenTelemetry SDK limit on attribute value length. Claude Code caps content-bearing telemetry attributes at the smaller of this and
CLAUDE_CODE_OTEL_CONTENT_MAX_LENGTH, so the truncation marker stays within the SDK limit. Claude Code reads the OTEL_LOGRECORD_ATTRIBUTE_VALUE_LENGTH_LIMIT and OTEL_SPAN_ATTRIBUTE_VALUE_LENGTH_LIMIT variants the same way, and the smallest set value applies to all signals. Requires Claude Code v2.1.214 or later. See MonitoringOTEL_LOG_ASSISTANT_RESPONSES
Telemetry
Set to
1 to include the model's response text on assistant_response OpenTelemetry log events. When unset, Claude Code uses the value of OTEL_LOG_USER_PROMPTS instead. Set to 0 to keep responses redacted even when OTEL_LOG_USER_PROMPTS is set. Set it in your shell, user settings, or managed settings. Ignored in project and local settings. Requires Claude Code v2.1.193 or later. See MonitoringOTEL_LOG_MANAGED_SETTINGS
Telemetry
Set to
1 to add the redacted managed settings, and a SHA-256 digest of the settings before redaction, to managed_settings_resolved OpenTelemetry log events. Disabled by default. Set it in your shell, user settings, or managed settings; a value in project or local settings doesn't turn it on. Requires Claude Code v2.1.274 or later. See MonitoringOTEL_LOG_RAW_API_BODIES
Telemetry
Emit Anthropic Messages API request and response JSON as
api_request_body / api_response_body log events. Set to 1 for inline bodies truncated at the content limit, or file:<dir> to write untruncated bodies to disk and emit a body_ref path instead. CLAUDE_CODE_OTEL_CONTENT_MAX_LENGTH configures the content limit, 60 KB by default. Disabled by default; bodies include the entire conversation history. Set it in your shell, user settings, or managed settings. Ignored in project and local settings. See MonitoringOTEL_LOG_TOOL_CONTENT
Telemetry
Set to
1 to include tool content in the tool.output OpenTelemetry span event. Span attributes carry tool content under their own gates. Requires tracing. Disabled by default to protect sensitive data. Set it in your shell, user settings, or managed settings. Ignored in project and local settings, apart from the off values that section describes. See MonitoringOTEL_LOG_TOOL_DETAILS
Telemetry
Set to
1 to include tool input arguments; MCP server names; user-authored workflow names; raw error strings on tool failures; the refusal category on api_refusal events; real agent, skill, plugin, and MCP server names on cost and token metrics; and other tool details in OpenTelemetry metrics, traces, and logs. Disabled by default to protect PII. Set it in your shell, user settings, or managed settings. Ignored in project and local settings, apart from the off values that section describes. See MonitoringOTEL_LOG_USER_PROMPTS
Telemetry
Set to
1 to include user prompt text in OpenTelemetry traces and logs. Disabled by default (prompts are redacted). Set it in your shell, user settings, or managed settings. Ignored in project and local settings, apart from the off values that section describes. See MonitoringOTEL_METRICS_INCLUDE_ACCOUNT_UUID
Telemetry
Set to
false to exclude account UUID from metrics attributes (default: included). See MonitoringOTEL_METRICS_INCLUDE_ENTRYPOINT
Telemetry
Set to
true to include the session entrypoint in metrics attributes (default: excluded). Added in v2.1.152. See MonitoringOTEL_METRICS_INCLUDE_REPOSITORY
Telemetry
Set to
true to tag OpenTelemetry metrics and events with vcs.* attributes identifying the session's repository (default: excluded). Requires Claude Code v2.1.269 or later. See Repository attributesAs of v2.1.161, Claude Code attaches
OTEL_RESOURCE_ATTRIBUTES keys to metric datapoint labels. Set to false to exclude them (default: included). See MonitoringOTEL_METRICS_INCLUDE_SESSION_ID
Telemetry
Set to
false to exclude session ID from metrics attributes (default: included). See MonitoringOTEL_METRICS_INCLUDE_VERSION
Telemetry
Set to
true to include Claude Code version in metrics attributes (default: excluded). See MonitoringOverride the character budget for skill metadata shown to the Skill tool. The budget scales dynamically at 1% of the context window, with a fallback of 8,000 characters. Legacy name kept for backwards compatibility
Removed in v2.1.277 and now a no-op, together with the
TaskOutput tool it sized. Previously set the maximum number of characters of a background task's output that the TaskOutput tool kept. Claude reads a background task's output file with Read insteadUSE_BUILTIN_RIPGREP
Other
Set to
0 to use system-installed rg instead of rg included with Claude CodeVERTEX_REGION_CLAUDE_3_5_HAIKU
Cloud providers
Override region for Claude 3.5 Haiku when using Google Cloud's Agent Platform
VERTEX_REGION_CLAUDE_3_5_SONNET
Cloud providers
Override region for Claude 3.5 Sonnet when using Google Cloud's Agent Platform
VERTEX_REGION_CLAUDE_3_7_SONNET
Cloud providers
Override region for Claude 3.7 Sonnet when using Google Cloud's Agent Platform
VERTEX_REGION_CLAUDE_4_0_OPUS
Cloud providers
Override region for Claude Opus 4 when using Google Cloud's Agent Platform
VERTEX_REGION_CLAUDE_4_0_SONNET
Cloud providers
Override region for Claude Sonnet 4 when using Google Cloud's Agent Platform
VERTEX_REGION_CLAUDE_4_1_OPUS
Cloud providers
Override region for Claude Opus 4.1 when using Google Cloud's Agent Platform
VERTEX_REGION_CLAUDE_4_5_OPUS
Cloud providers
Override region for Claude Opus 4.5 when using Google Cloud's Agent Platform
VERTEX_REGION_CLAUDE_4_5_SONNET
Cloud providers
Override region for Claude Sonnet 4.5 when using Google Cloud's Agent Platform
VERTEX_REGION_CLAUDE_4_6_OPUS
Cloud providers
Override region for Claude Opus 4.6 when using Google Cloud's Agent Platform
VERTEX_REGION_CLAUDE_4_6_SONNET
Cloud providers
Override region for Claude Sonnet 4.6 when using Google Cloud's Agent Platform
VERTEX_REGION_CLAUDE_4_7_OPUS
Cloud providers
Override region for Claude Opus 4.7 when using Google Cloud's Agent Platform
VERTEX_REGION_CLAUDE_4_8_OPUS
Cloud providers
Override region for Claude Opus 4.8 when using Google Cloud's Agent Platform
VERTEX_REGION_CLAUDE_5_5_OPUS
Cloud providers
Override region for Claude Opus 5.5 when using Google Cloud's Agent Platform. Added in v2.1.280
VERTEX_REGION_CLAUDE_5_5_SONNET
Cloud providers
Override region for Claude Sonnet 5.5 when using Google Cloud's Agent Platform. Added in v2.1.284
VERTEX_REGION_CLAUDE_5_OPUS
Cloud providers
Override region for Claude Opus 5 when using Google Cloud's Agent Platform. Added in v2.1.219
VERTEX_REGION_CLAUDE_5_SONNET
Cloud providers
Override region for Claude Sonnet 5 when using Google Cloud's Agent Platform. Added in v2.1.197
VERTEX_REGION_CLAUDE_FABLE_5
Cloud providers
Override region for Claude Fable 5 when using Google Cloud's Agent Platform. Added in v2.1.170
VERTEX_REGION_CLAUDE_FABLE_5_1
Cloud providers
Override region for Claude Fable 5.1 when using Google Cloud's Agent Platform. Added in v2.1.257
VERTEX_REGION_CLAUDE_HAIKU_4_5
Cloud providers
Override region for Claude Haiku 4.5 when using Google Cloud's Agent Platform
VERTEX_REGION_CLAUDE_HAIKU_5_5
Cloud providers
Override region for Claude Haiku 5.5 when using Google Cloud's Agent Platform. Added in v2.1.293
Setting variables in settings.json
Put variables you always want under env in a settings file so you do not have to export them in every shell:
{
"env": {
"ANTHROPIC_MODEL": "claude-opus-5-5",
"BASH_DEFAULT_TIMEOUT_MS": "300000"
}
}Build the rest of the file with the settings.json generator.
Frequently asked questions
Where do I set Claude Code environment variables?
Either export them in your shell before running claude, or put them under the "env" key in settings.json (~/.claude/settings.json for all projects, .claude/settings.json for one project). Settings-file values apply to every session and to the commands Claude runs.
Does ANTHROPIC_API_KEY override my Claude subscription?
Yes. When ANTHROPIC_API_KEY is set, Claude Code uses the key and bills the API account instead of your Pro, Max, Team or Enterprise plan. In interactive mode it asks you to approve the key once; in -p mode it always uses it. Unset it to go back to your subscription.
How do I use Claude Code with Amazon Bedrock or Google Vertex?
Set CLAUDE_CODE_USE_BEDROCK=1 or CLAUDE_CODE_USE_VERTEX=1 along with the provider's normal credentials and region variables. Filter this page by "Cloud providers" for the full list.
How do I change the default model with an environment variable?
Set ANTHROPIC_MODEL to an alias or full model ID. ANTHROPIC_DEFAULT_OPUS_MODEL, ANTHROPIC_DEFAULT_SONNET_MODEL and ANTHROPIC_DEFAULT_HAIKU_MODEL change what each alias resolves to, which is handy on cloud providers.
Sources: Claude Code environment variables. Claude Code Agents is an independent site, not affiliated with Anthropic.
More free Claude Code tools
All tools →CLI flagsEvery claude command and flag: -p, --continue, --model, --allowedTools and the rest.settings.json generatorPick a model, permission mode, allow and deny rules, env vars and more. Get a valid .claude/settings.json.Claude models & IDsCurrent Claude model IDs, context windows, pricing and Claude Code aliases.Claude Code cheat sheetThe commands, shortcuts, flags and files you use every day, on one printable page.