Class●Since v0.0
Settings
Global settings and environment detection for deepagents-cli.
This class is initialized once at startup and provides access to:
- Available models and API keys
- Current project information
- Tool availability (e.g., Tavily)
- File system paths
Settings(
self,
openai_api_key: str | None,
anthropic_api_key: str | None,
google_api_key: str | None,
nvidia_api_key: str | None,
tavily_api_key: str | None,
google_cloud_project: str | None,
deepagents_langchain_project: str | None,
user_langchain_project: str | None,
model_name: str | None = None,
model_provider: str | None = None,
model_context_limit: int | None = None,
project_root: Path | None = None,
shell_allow_list: list[str] | None = None
)Constructors
constructor
__init__
| Name | Type |
|---|---|
| openai_api_key | str | None |
| anthropic_api_key | str | None |
| google_api_key | str | None |
| nvidia_api_key | str | None |
| tavily_api_key | str | None |
| google_cloud_project | str | None |
| deepagents_langchain_project | str | None |
| user_langchain_project | str | None |
| model_name | str | None |
| model_provider | str | None |
| model_context_limit | int | None |
| project_root | Path | None |
| shell_allow_list | list[str] | None |
Attributes
attributeattributeattributeattributeattributeattributeattributeattributeattributeattributeattributeattributeattributeattributeattributeattributeattributeattributeattributeattributeattribute
openai_api_key: str | None
anthropic_api_key: str | None
google_api_key: str | None
nvidia_api_key: str | None
tavily_api_key: str | None
google_cloud_project: str | None
deepagents_langchain_project: str | None
user_langchain_project: str | None
model_name: str | None
model_provider: str | None
model_context_limit: int | None
project_root: Path | None
shell_allow_list: list[str] | None
has_openai: bool
Check if OpenAI API key is configured.
has_anthropic: bool
Check if Anthropic API key is configured.
has_google: bool
Check if Google API key is configured.
has_nvidia: bool
Check if NVIDIA API key is configured.
has_vertex_ai: bool
Check if VertexAI is available (Google Cloud project set, no API key).
VertexAI uses Application Default Credentials (ADC) for authentication, so if GOOGLE_CLOUD_PROJECT is set and GOOGLE_API_KEY is not, we assume VertexAI.
has_tavily: bool
Check if Tavily API key is configured.
user_deepagents_dir: Path
Get the base user-level .deepagents directory.
user_agents_dir: Path
Get the base user-level .agents directory (~/.agents).
Methods
methodmethodmethodmethodmethodmethodmethodmethodmethodmethodmethodmethodmethodmethodmethod
from_environment
Create settings by detecting the current environment.
reload_from_environment
Reload selected settings from environment variables and project files.
This refreshes only fields that are expected to change at runtime (API keys, Google Cloud project, project root, shell allow-list, and LangSmith tracing project).
Runtime model state (model_name, model_provider,
model_context_limit) and the original user LangSmith project
(user_langchain_project) are intentionally preserved -- they are
not in reloadable_fields and are never touched by this method.
get_user_agent_md_path
Get user-level AGENTS.md path for a specific agent.
Returns path regardless of whether the file exists.
get_project_agent_md_path
Get project-level AGENTS.md paths.
Checks both {project_root}/.deepagents/AGENTS.md and
{project_root}/AGENTS.md, returning all that exist. If both are
present, both are loaded and their instructions are combined, with
.deepagents/AGENTS.md first.
get_agent_dir
Get the global agent directory path.
ensure_agent_dir
Ensure the global agent directory exists and return its path.
get_user_skills_dir
Get user-level skills directory path for a specific agent.
ensure_user_skills_dir
Ensure user-level skills directory exists and return its path.
get_project_skills_dir
Get project-level skills directory path.
ensure_project_skills_dir
Ensure project-level skills directory exists and return its path.
get_user_agents_dir
Get user-level agents directory path for custom subagent definitions.
get_project_agents_dir
Get project-level agents directory path for custom subagent definitions.
get_user_agent_skills_dir
Get user-level ~/.agents/skills/ directory.
This is a generic alias path for skills that is tool-agnostic.
get_project_agent_skills_dir
Get project-level .agents/skills/ directory.
This is a generic alias path for skills that is tool-agnostic.
get_built_in_skills_dir
Get the directory containing built-in skills that ship with the CLI.