Environment variables

Mirri 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 KIMI_API_KEY, ANTHROPIC_API_KEY, and OPENAI_API_KEY are not read automatically from shell environment variables. Running export KIMI_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 MIRRICODE_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

MIRRICODE_HOME

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

export MIRRICODE_HOME="/path/to/custom/mirri-code"

Make sure the directory is writable. Multiple mirri instances sharing the same MIRRICODE_HOME will share config and credential files.

For the complete data directory structure, see Data locations.

MIRRICODE_DISABLE_TELEMETRY

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

export MIRRICODE_DISABLE_TELEMETRY=1

MIRRICODE_MODEL_* family

Switch models temporarily without modifying config.toml — when MIRRICODE_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.

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]
KIMI_API_KEY = "sk-xxx"
KIMI_BASE_URL = "https://api.moonshot.ai/v1"

Key names per provider:

Key	Applicable provider	Default
KIMI_API_KEY	Kimi / Mirri	None
KIMI_BASE_URL	Kimi / Mirri	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
MIRRICODE_OAUTH_HOST	OAuth auth host; highest priority	Falls back to MIRRICODE_OAUTH_HOST when unset
MIRRICODE_OAUTH_HOST	OAuth auth host; fallback for MIRRICODE_OAUTH_HOST	Falls back to https://auth.kimi.com when unset
MIRRICODE_BASE_URL	Managed API base URL used after OAuth login	https://api.kimi.com/coding/v1

WARNING

MIRRICODE_BASE_URL (OAuth-managed service, targeting kimi.com) and KIMI_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 (MIRRICODE_MODEL_*)

Want to switch models for testing without touching config.toml? When MIRRICODE_MODEL_NAME is set, the CLI synthesizes a temporary provider and model alias from the MIRRICODE_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 MIRRICODE_MODEL_NAME="kimi-for-coding"
export MIRRICODE_MODEL_API_KEY="YOUR_API_KEY"
export MIRRICODE_MODEL_BASE_URL="https://api.example.com/v1"
export MIRRICODE_MODEL_MAX_CONTEXT_SIZE="262144"
export MIRRICODE_MODEL_CAPABILITIES="image_in,thinking"
mirri

Complete variable list:

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

If MIRRICODE_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
MIRRICODE_DISABLE_TELEMETRY	Disable anonymous telemetry reporting	1, true, yes, y (case-insensitive)
MIRRICODE_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
MIRRICODE_PLUGIN_MARKETPLACE_URL	Override the plugin marketplace JSON loaded by /plugins; useful for dev loopback servers, staging CDN files, or alternate marketplace directories	https://mirricode.com/plugins/marketplace.json; also accepts http://, file:// URLs, and local paths
MIRRICODE_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
MIRRICODE_EXPERIMENTAL_FLAG	Enable all registered experimental features for this process	1, true, yes, on
MIRRICODE_SHELL_PATH	Override the Git Bash path on Windows (used when auto-detection fails)	Absolute path
MIRRICODE_MODEL_MAX_COMPLETION_TOKENS	Hard cap on max_completion_tokens per LLM step; applies to the mirri provider only	Positive integer; 0 or negative disables clamping
MIRRICODE_MODEL_TEMPERATURE	Sampling temperature for every request; applies to the mirri provider only (global — independent of MIRRICODE_MODEL_NAME)	Number, e.g. 0.3
MIRRICODE_MODEL_TOP_P	Nucleus-sampling top_p for every request; applies to the mirri provider only (global)	Number, e.g. 0.95
MIRRICODE_MODEL_THINKING_EFFORT	Force a specific thinking effort on the wire (thinking.effort), bypassing the model's declared support_efforts; applies to the mirri provider only, and only while Thinking is on	An effort value, e.g. max
MIRRICODE_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
MIRRICODE_NO_AUTO_UPDATE	Fully disable the update preflight — no check, background install, or prompt. Legacy alias MIRRICODE_CLI_NO_AUTO_UPDATE is also honored	Truthy: 1/true/yes/on
MIRRICODE_DISABLE_CRON	Disable the scheduled-task tool (CronCreate rejects new schedules; existing tasks do not fire)	1 to disable

Diagnostic logs

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

Variable	Purpose	Default
MIRRICODE_LOG_LEVEL	Log level: off, error, warn, info, debug	info
MIRRICODE_LOG_GLOBAL_MAX_BYTES	Maximum bytes per global log file	6291456 (6 MB)
MIRRICODE_LOG_GLOBAL_FILES	Number of global log files to retain	5
MIRRICODE_LOG_SESSION_MAX_BYTES	Maximum bytes per session log file	5242880 (5 MB)
MIRRICODE_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

Mirri 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 Mirri 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 MIRRICODE_HOME
• Providers and models — full connection examples per provider type