Environment variables

Jarvis Code CLI uses environment variables to control a small number of runtime behaviors — relocating the data directory, turning off telemetry, and temporarily switching models without touching the config file.

Important: API keys are not configured here

Credential variables such as JARVIS_API_KEY, ANTHROPIC_API_KEY, and OPENAI_API_KEY are not read automatically from shell environment variables. Running export JARVIS_API_KEY=xxx in the terminal does not give any provider its key — they must be written in config.toml under [providers.<name>] or the [providers.<name>.env] sub-table.

The only exception is the JARVIS_MODEL_* family, which is an explicit channel that does read credentials from the shell — see Define a model from environment variables.

For background, see Config overrides: provider credentials.

Core paths

JARVIS_CODE_HOME

Overrides the data root directory; the default is ~/.jarvis-code. Once set, the config file, sessions, logs, OAuth credentials, and all other data land under the new path:

export JARVIS_CODE_HOME="/path/to/custom/jarvis-code"

Make sure the directory is writable. Multiple Jarvis Code instances sharing the same JARVIS_CODE_HOME will share config and credential files.

For the complete data directory structure, see Data locations.

JARVIS_DISABLE_TELEMETRY

Set to 1 to turn off anonymous telemetry reporting (also accepts true, yes, y, case-insensitive):

export JARVIS_DISABLE_TELEMETRY=1

JARVIS_MODEL_* family

Switch models temporarily without modifying config.toml — when JARVIS_MODEL_NAME is set, the CLI synthesizes a temporary provider in memory; the change does not persist after restart. See Define a model from environment variables.

JARVIS_CODE_CUSTOM_HEADERS

Attaches custom HTTP headers to every outbound model request — both LLM chat requests (across all provider protocols) and /models listing requests. Useful when a gateway routes by header, for example to pin a specific cluster:

export JARVIS_CODE_CUSTOM_HEADERS=$'X-Gateway-Cluster: my-cluster\nX-Custom-Tag: debug'

The format mirrors ANTHROPIC_CUSTOM_HEADERS: newline-separated Name: Value lines. Names and values are trimmed, and lines without a colon are ignored.

Added

Added in 0.20.2.

Precedence: the Kimi identity headers (User-Agent, X-Msh-*) and a provider's custom_headers in config.toml (see Config files) override same-named entries here. Authentication is protocol-dependent: on the kimi, openai, and openai_responses protocols an exact Authorization entry replaces the generated bearer token, while /models listing requests keep their own authentication. A case variant such as authorization is never treated as the same name — it is combined with the real header, which can break requests. Do not use this variable for authentication or other reserved headers. Use custom_headers when headers need to differ per provider.

Provider credential key names (written in config.toml)

The key names below are not read directly from the shell — they are key names written inside the [providers.<name>.env] sub-table of config.toml, serving as fallback values for api_key / base_url. The CLI reads only from the config file, not from process.env.

This design lets you keep familiar key name conventions while centralizing secret management in the config file:

[providers.kimi.env]
JARVIS_API_KEY = "sk-xxx"
JARVIS_BASE_URL = "https://api.moonshot.ai/v1"

Key names per provider:

Key	Applicable provider	Default
JARVIS_API_KEY	Kimi / Moonshot	None
JARVIS_BASE_URL	Kimi / Moonshot	https://api.moonshot.ai/v1
ANTHROPIC_API_KEY	Anthropic	None
ANTHROPIC_BASE_URL	Anthropic	Follows Anthropic SDK default
OPENAI_API_KEY	OpenAI (openai and openai_responses)	None
OPENAI_BASE_URL	OpenAI (openai and openai_responses)	https://api.openai.com/v1
GOOGLE_API_KEY	Google GenAI, Vertex AI	None
VERTEXAI_API_KEY	Vertex AI	None
GOOGLE_CLOUD_PROJECT	Vertex AI	None
GOOGLE_CLOUD_LOCATION	Vertex AI	None

WARNING

GOOGLE_APPLICATION_CREDENTIALS (path to a service account JSON file) is the only exception that goes through the system environment variable mechanism — it is read by the Google SDK directly via the standard ADC flow, and the CLI does not participate. All other key names must be placed in the [providers.<name>.env] sub-table to take effect.

For the full provider type and field reference, see Providers and models.

OAuth and managed services

This group of variables redirects OAuth authentication and managed service endpoints to a self-hosted or test environment. They are not needed for everyday use.

Variable	Purpose	Default
JARVIS_CODE_OAUTH_HOST	OAuth auth host; highest priority	Falls back to JARVIS_OAUTH_HOST when unset
JARVIS_OAUTH_HOST	OAuth auth host; fallback for JARVIS_CODE_OAUTH_HOST	Falls back to https://auth.kimi.com when unset
JARVIS_CODE_BASE_URL	Managed API base URL used after OAuth login	https://api.kimi.com/coding/v1

WARNING

JARVIS_CODE_BASE_URL (OAuth-managed service, targeting kimi.com) and JARVIS_BASE_URL (direct API key connection, targeting moonshot.ai) are two distinct variables. Use each one in its appropriate context.

Define a model from environment variables (JARVIS_MODEL_*)

Want to switch models for testing without touching config.toml? When JARVIS_MODEL_NAME is set, the CLI synthesizes a temporary provider and model alias from the JARVIS_MODEL_* variables in memory — nothing is written back to the config file. These variables take priority over default_model in config.toml, but the -m <alias> option at startup still has the highest priority.

export JARVIS_MODEL_NAME="kimi-for-coding"
export JARVIS_MODEL_API_KEY="YOUR_API_KEY"
export JARVIS_MODEL_BASE_URL="https://api.example.com/v1"
export JARVIS_MODEL_MAX_CONTEXT_SIZE="262144"
export JARVIS_MODEL_CAPABILITIES="image_in,thinking"
jarvis

Complete variable list:

Variable	Required	Purpose	Default
JARVIS_MODEL_NAME	Yes (also the enable switch)	Model id sent to the API	—
JARVIS_MODEL_API_KEY	Yes	API key	—
JARVIS_MODEL_PROVIDER_TYPE	No	Provider type: kimi, anthropic, openai	kimi
JARVIS_MODEL_BASE_URL	No	API base URL	Each type has its own default
JARVIS_MODEL_MAX_CONTEXT_SIZE	No	Maximum context length (tokens)	262144 (256 K)
JARVIS_MODEL_CAPABILITIES	No	Comma-separated capability tags, unioned with auto-detected capabilities	image_in,thinking
JARVIS_MODEL_DISPLAY_NAME	No	Name shown in /model	Falls back to JARVIS_MODEL_NAME
JARVIS_MODEL_MAX_OUTPUT_SIZE	No	Per-request output cap (anthropic only); when set, overrides the built-in Claude ceiling	Model default
JARVIS_MODEL_REASONING_KEY	No	Reasoning field name override (openai only)	Auto-detected
JARVIS_MODEL_THINKING_EFFORT	No	Thinking effort level: low/medium/high/xhigh/max	—
JARVIS_MODEL_ADAPTIVE_THINKING	No	Force adaptive thinking on or off (anthropic only)	Inferred from model name

If JARVIS_MODEL_NAME is set but a required variable is missing, startup fails immediately with a clear error message.

Runtime switches

Switches that control the behavior of subsystems such as telemetry, background tasks, and the plugin marketplace:

Variable	Purpose	Valid values
JARVIS_DISABLE_TELEMETRY	Disable anonymous telemetry reporting	1, true, yes, y (case-insensitive)
JARVIS_CODE_PASSWORD	Set a parallel auth credential for the jarvis server API, valid alongside the bearer token; recommended when binding the server beyond loopback — see Local server and API	Any non-empty string; when unset, only the token is valid
JARVIS_CODE_BACKGROUND_KEEP_ALIVE_ON_EXIT	Whether to keep background tasks when the session closes; takes higher priority than config.toml. The default is to stop them on exit	Truthy: 1/true/yes/on; falsy: 0/false/no/off
JARVIS_CODE_BACKGROUND_MAX_RUNNING_TASKS	Cap on concurrently running background tasks; takes higher priority than [background] max_running_tasks in config.toml (unset means no cap)	Positive integer; invalid values are ignored
JARVIS_IMAGE_MAX_EDGE_PX	Longest-edge ceiling (px) for image compression; takes higher priority than [image] max_edge_px in config.toml (default 2000)	Positive integer; invalid values are ignored
JARVIS_IMAGE_READ_BYTE_BUDGET	Per-image byte budget for model-initiated image reads (ReadMediaFile default reads); takes higher priority than [image] read_byte_budget in config.toml (default 262144, i.e. 256 KB)	Positive integer; invalid values are ignored
JARVIS_CODE_PLUGIN_MARKETPLACE_URL	Override the plugin marketplace JSON loaded by /plugins; useful for dev loopback servers, staging CDN files, or alternate marketplace directories	https://code.kimi.com/kimi-code/plugins/marketplace.json; also accepts http://, file:// URLs, and local paths
JARVIS_CODE_AGENT_SWARM_MAX_CONCURRENCY	Cap how many AgentSwarm subagents run concurrently during the initial ramp; leave unset for no cap	Positive integer; invalid values fail fast
JARVIS_SUBAGENT_TIMEOUT_MS	Maximum wall-clock time (ms) a single Agent subagent may run; takes higher priority than [subagent] timeout_ms in config.toml (default 7200000, i.e. 2 hours)	Positive integer; invalid values fall back to the config or default
JARVIS_CODE_SWARM_TIMEOUT_MS	Maximum wall-clock time (ms) a single AgentSwarm subagent may run; takes higher priority than [swarm] timeout_ms in config.toml (default 7200000, i.e. 2 hours)	Positive integer; invalid values fall back to the config or default
JARVIS_CODE_IDENTITY_NAME	Display name the agent calls itself in the system prompt; takes higher priority than [identity] name in config.toml and is never written back to it	Any non-empty string; blank values read as unset
JARVIS_CODE_IDENTITY_SLUG	Protocol identifier for the User-Agent product token sent to third-party providers and the MCP client name; takes higher priority than [identity] slug. Derived from the name when unset	Any non-empty string; normalized to lowercase with non-alphanumeric runs folded to -
JARVIS_CODE_BUILTIN_PRODUCT_SKILLS	Whether the built-in skills documenting Jarvis Code itself are offered to the model; takes higher priority than builtin_product_skills in config.toml (default enabled)	Truthy: 1/true/yes/on; falsy: 0/false/no/off
JARVIS_CODE_TUI_FULL_SCREEN	Enable the experimental fullscreen alternate-screen UI: scrollable transcript viewport, mouse text selection, clickable links, and Ctrl-Shift-F transcript search	1 enables it; anything else keeps the regular inline UI
JARVIS_CODE_EXPERIMENTAL_SECONDARY_MODEL	Enable the experimental subagent model pool in every launch mode, including the interactive TUI; the master JARVIS_CODE_EXPERIMENTAL_FLAG=1 also enables it	Truthy: 1/true/yes/on; falsy: 0/false/no/off
JARVIS_SECONDARY_MODEL	Secondary model; takes higher priority than [secondary_model] model in config.toml. When the secondary-model experiment is enabled, newly spawned subagents (Agent / AgentSwarm) bind to it by default instead of inheriting the main agent's model	The alias of a configured [models] entry, e.g. jarvis-code/kimi-for-coding; blank values are ignored
JARVIS_SECONDARY_EFFORT	Thinking effort for the secondary model; takes higher priority than [secondary_model] default_effort in config.toml and applies only when both the model and its experiment are enabled	An effort value, e.g. low; blank values are ignored
JARVIS_CODE_EXPERIMENTAL_SUBAGENT_FORK	Enable the experimental fork parameter on the Agent and AgentSwarm tools, letting the model start a subagent with a snapshot of the calling agent's conversation history instead of an empty context; the master JARVIS_CODE_EXPERIMENTAL_FLAG=1 also enables it	Truthy: 1/true/yes/on; falsy: 0/false/no/off
JARVIS_MCP_STARTUP_TIMEOUT_MS	Global default connection timeout (ms) for all MCP servers; takes higher priority than [mcp] startup_timeout_ms in config.toml, but a per-server startupTimeoutMs in mcp.json still wins (default 30000)	Integer from 1 to 2147483647; invalid values are ignored
JARVIS_MCP_TOOL_TIMEOUT_MS	Global default single tool-call timeout (ms) for all MCP servers; takes higher priority than [mcp] tool_timeout_ms in config.toml, but a per-server toolTimeoutMs in mcp.json still wins (default 60000)	Integer from 1 to 2147483647; invalid values are ignored
JARVIS_LOOP_MAX_STEPS_PER_TURN	Maximum Agent steps per turn; takes higher priority than [loop_control] max_steps_per_turn in config.toml (unset or 0 means unlimited)	Non-negative integer; invalid values are ignored
JARVIS_LOOP_MAX_ATTEMPTS_PER_STEP	Maximum total attempts for a failing step (including the initial attempt); takes higher priority than [loop_control] max_attempts_per_step in config.toml (default 10). The deprecated JARVIS_LOOP_MAX_RETRIES_PER_STEP is still honored with a warning when this variable is unset	Non-negative integer; invalid values are ignored
JARVIS_CODE_INFINITE_RETRY	Retry every failed LLM request indefinitely — turn steps and background operations such as compaction alike — instead of failing the task; waits use exponential backoff (capped at 32 s) and honor the server's Retry-After header, and aborting still cancels immediately. Intended for long-running unattended evaluations against endpoints that may fail temporarily	Truthy: 1/true/yes/on; falsy: 0/false/no/off
JARVIS_TOKEN_COUNTING_STRATEGY	Which context token count is reported externally (the context-size display); takes higher priority than [token_counting] strategy in config.toml (default measured+estimated)	measured+estimated, measured, estimated (case-insensitive); invalid values are ignored
JARVIS_WEB_SEARCH_BASE_URL	API URL of the web search (WebSearch) service; takes higher priority than [services.moonshot_search] base_url in config.toml, and enables the service without that config section. Persisted credentials and custom headers are not forwarded to an env-selected endpoint	Non-blank string; blank values are ignored
JARVIS_WEB_SEARCH_API_KEY	API key of the web search (WebSearch) service; replaces both the configured API key and OAuth credential when set	Non-blank string; blank values are ignored
JARVIS_WEB_FETCH_BASE_URL	API URL of the web fetch (FetchURL) service; takes higher priority than [services.moonshot_fetch] base_url. Persisted credentials and custom headers are not forwarded to an env-selected endpoint. Without an env or config endpoint, signed-in users try the managed Kimi OAuth fetch service before direct local requests	Non-blank string; blank values are ignored
JARVIS_WEB_FETCH_API_KEY	API key of the web fetch (FetchURL) service; replaces both the configured API key and OAuth credential when set	Non-blank string; blank values are ignored
JARVIS_BRAVE_BASE_URL	API URL of the Brave Search backend; takes higher priority than [services.brave] base_url in config.toml. Persisted credentials and custom headers are not forwarded to an env-selected endpoint. Read by the default agent-core-v2 engine only	Non-blank string; blank values are ignored
JARVIS_BRAVE_API_KEY	API key of the Brave Search backend; takes higher priority than [services.brave] api_key. Requires active_search_provider = "brave" to serve WebSearch. Read by the default agent-core-v2 engine only	Non-blank string; blank values are ignored
JARVIS_CODE_EXPERIMENTAL_FLAG	Master switch: enable every registered experimental feature for this process; it does not select the agent engine. See Experimental flags	1, true, yes, on
JARVIS_CODE_EXPERIMENTAL_TOWER	Enable Tower mode; engine v2 only, and a restart is required after enabling	Truthy: 1/true/yes/on; falsy: 0/false/no/off
JARVIS_CODE_EXPERIMENTAL_AUTO_SESSION_TITLE	Enable AI-generated session titles; requires a managed OAuth login	Truthy: 1/true/yes/on; falsy: 0/false/no/off
JARVIS_CODE_EXPERIMENTAL_TOOL_SELECT	Enable progressive tool disclosure so MCP tool schemas load on demand; legacy engine only	Truthy: 1/true/yes/on; falsy: 0/false/no/off
JARVIS_CODE_EXPERIMENTAL_PERSISTENCE_MINIDB_READMODEL	Use the minidb-backed read model for session indexing and wire replay; on by default	Truthy: 1/true/yes/on; falsy: 0/false/no/off
JARVIS_CODE_EXPERIMENTAL_SEARCH_WORKER	Run the global search index in a dedicated worker thread; on by default	Truthy: 1/true/yes/on; falsy: 0/false/no/off
JARVIS_CODE_LEGACY_FLAG	Use the legacy agent-core engine for jarvis, jarvis -p, jarvis doctor, jarvis acp, jarvis export, and jarvis provider; these commands use agent-core-v2 by default	1, true, yes, on
JARVIS_SHELL_PATH	Override the Git Bash path on Windows (used when auto-detection fails)	Absolute path
JARVIS_MODEL_MAX_COMPLETION_TOKENS	Hard cap on max_completion_tokens per LLM step; applies to the kimi provider only	Positive integer; 0 or negative disables clamping
JARVIS_MODEL_TEMPERATURE	Sampling temperature for every request; applies to the kimi provider only (global — independent of JARVIS_MODEL_NAME)	Number, e.g. 0.3
JARVIS_MODEL_TOP_P	Nucleus-sampling top_p for every request; applies to the kimi provider only (global)	Number, e.g. 0.95
JARVIS_MODEL_THINKING_EFFORT	Force a specific thinking effort on the wire (thinking.effort), bypassing the model's declared support_efforts; applies to the kimi provider only, and only while Thinking is on	An effort value, e.g. max
JARVIS_MODEL_THINKING_KEEP	Preserved-thinking passthrough; on kimi sent as thinking.keep, on anthropic (Claude and Kimi's Anthropic-compatible mode) sent as a context_management clear_thinking_20251015 edit (enabling keep routes Anthropic requests to the beta Messages API); overrides [thinking] keep (which defaults to "all"); only injected while Thinking is on	A value the API accepts, e.g. all; an off-value (false/0/no/off/none/null) disables it
JARVIS_VISUAL_MODEL	Alias of the visual model used for image / screenshot / video inspection tasks; takes higher priority than [visual_model] model in config.toml. While set, it never leaks into config.toml. Read by the default agent-core-v2 engine only	Alias of a configured [models] entry
JARVIS_VISUAL_EFFORT	Thinking effort applied when visual tasks bind the visual model; takes higher priority than [visual_model] default_effort	An effort value, e.g. low
JARVIS_CODE_NO_AUTO_UPDATE	Fully disable the update preflight — no check, background install, or prompt. Legacy alias JARVIS_CLI_NO_AUTO_UPDATE is also honored	Truthy: 1/true/yes/on
JARVIS_DISABLE_CRON	Disable the scheduled-task tool (CronCreate rejects new schedules; existing tasks do not fire)	1 to disable

The JARVIS_CODE_INFINITE_RETRY, JARVIS_CODE_IDENTITY_*, and JARVIS_CODE_BUILTIN_PRODUCT_SKILLS variables are read by the default agent-core-v2 engine. The legacy jarvis / jarvis -p path selected with JARVIS_CODE_LEGACY_FLAG=1 ignores them. Conversely, JARVIS_SECONDARY_MODEL and JARVIS_SECONDARY_EFFORT are read by the legacy engine only, and the default engine ignores them. JARVIS_CODE_EXPERIMENTAL_SECONDARY_MODEL is read by both engines: it gates the v2 subagent model pool and the legacy secondary-model recipe.

Experimental flags

Experimental features are registered per engine domain and each one declares its own environment variable. JARVIS_CODE_EXPERIMENTAL_FLAG=1 is the master switch that enables every registered flag for the process; it does not select the agent engine. A flag that defaults to on is turned off by setting its variable to a falsy value.

Flag id	Environment variable	Default	What it does
tower	JARVIS_CODE_EXPERIMENTAL_TOWER	off	Tower mode: coordinate several agents on one objective, toggled with /tower. Engine v2 only, and a restart is required after enabling
secondary-model	JARVIS_CODE_EXPERIMENTAL_SECONDARY_MODEL	off	The subagent model pool. Read by both engines
subagent-fork	JARVIS_CODE_EXPERIMENTAL_SUBAGENT_FORK	off	The fork parameter on the Agent and AgentSwarm tools, starting a subagent from a snapshot of the caller's history
auto_session_title	JARVIS_CODE_EXPERIMENTAL_AUTO_SESSION_TITLE	off	AI-generated session titles through the managed chat_title tool. Requires a managed OAuth login
tool-select	JARVIS_CODE_EXPERIMENTAL_TOOL_SELECT	off	Progressive tool disclosure: keep MCP tool schemas out of the top-level tool list and let the model load them on demand. Legacy engine only
persistence_minidb_readmodel	JARVIS_CODE_EXPERIMENTAL_PERSISTENCE_MINIDB_READMODEL	on	Use the minidb-backed read model for session indexing and wire replay
search_worker	JARVIS_CODE_EXPERIMENTAL_SEARCH_WORKER	on	Run the global search index in a dedicated worker thread instead of the server main thread

Flags can also be set in the [experimental] section of config.toml, or toggled from the /experiments panel in the TUI. The environment variable takes priority over the config file.

Diagnostic logs

These variables control log level and file rotation, read once at process startup:

Variable	Purpose	Default
JARVIS_LOG_LEVEL	Log level: off, error, warn, info, debug	info
JARVIS_LOG_GLOBAL_MAX_BYTES	Maximum bytes per global log file	6291456 (6 MB)
JARVIS_LOG_GLOBAL_FILES	Number of global log files to retain	5
JARVIS_LOG_SESSION_MAX_BYTES	Maximum bytes per session log file	5242880 (5 MB)
JARVIS_LOG_SESSION_FILES	Number of session log files to retain	3

System environment variables

The CLI also reads several standard system variables to detect the runtime environment; it does not modify them:

• HOME: used to resolve the default data path
• VISUAL, EDITOR: external editor command (VISUAL takes precedence)
• PATH: used to locate dependencies such as rg, fd, fdfind, and git; on Windows, Git Bash detection checks each git.exe found on PATH, including package-manager shims such as Scoop
• NO_COLOR, FORCE_COLOR: control color output (following the no-color.org convention)
• CI: when non-empty and not "0", disables theme detection and falls back to the dark theme
• TERM_PROGRAM, TERM, TMUX: detect terminal features and notification support
• DISPLAY, WAYLAND_DISPLAY, XDG_SESSION_TYPE: detect Linux graphical sessions (for clipboard and image features)
• WSL_DISTRO_NAME, WSLENV: detect WSL for the clipboard PowerShell bridge
• LOCALAPPDATA: used on Windows as a fallback when probing for the Git Bash installation path

HTTP proxy

Jarvis Code honors the standard proxy environment variables for all outbound traffic — model API calls, MCP servers, web tools, telemetry, sign-in, and update checks:

• HTTP_PROXY / http_proxy: proxy for http:// requests
• HTTPS_PROXY / https_proxy: proxy for https:// requests
• ALL_PROXY / all_proxy: fallback proxy used when the scheme-specific variable is unset; this is where a SOCKS proxy is usually set
• NO_PROXY / no_proxy: comma-separated hosts that bypass the proxy

Both HTTP(S) and SOCKS proxies are supported. A SOCKS proxy is recognized by its scheme — socks5://, socks5h://, socks4://, or socks:// (an alias for socks5://) — and is typically set via ALL_PROXY (the form used by tools like Clash and V2RayN). An HTTP(S) proxy takes precedence over ALL_PROXY for HTTP/HTTPS traffic.

The proxy is applied only when one of these variables is set; otherwise connections are made directly. Loopback hosts (localhost, 127.0.0.1, ::1) always bypass the proxy, so a local server such as a localhost MCP server keeps working when a proxy is configured — add your own internal hosts to NO_PROXY to exempt them too.

Stdio MCP servers that run as Node child processes honor HTTP_PROXY / HTTPS_PROXY / NO_PROXY automatically when the child's Node version supports NODE_USE_ENV_PROXY (Node ≥ 22.21 or ≥ 24.5); SOCKS proxying applies to Jarvis Code's own traffic only.

Next steps

• Config overrides — how environment variables, CLI options, and the config file interact by priority
• Data locations — directory structure affected by JARVIS_CODE_HOME
• Providers and models — full connection examples per provider type