Module config_types 

Structs

CollaborationMode

Collaboration mode for a Codex session.

CollaborationModeMask

A mask for collaboration mode settings, allowing partial updates. All fields except name are optional, enabling selective updates.

ModelProviderAuthInfo

Configuration for obtaining a provider bearer token from a command.

PersonalityIter

An iterator over the variants of Personality

ProfileV2Name

Validated plain profile-v2 name used to select $CODEX_HOME/<name>.config.toml.

ProfileV2NameParseError

Settings

Settings for a collaboration mode.

ShellEnvironmentPolicy

Deriving the env based on this policy works as follows:

WebSearchConfig

WebSearchFilters

WebSearchLocation

WebSearchToolConfig

WebSearchUserLocation

Enums

AltScreenMode

Controls whether the TUI uses the terminal’s alternate screen buffer.

ApprovalsReviewer

Configures who approval requests are routed to for review. Examples include sandbox escapes, blocked network access, MCP approval prompts, and ARC escalations. Defaults to user. auto_review uses a carefully prompted subagent to gather relevant context and apply a risk-based decision framework before approving or denying the request.

AutoCompactTokenLimitScope

Selects which part of the active context is charged against model_auto_compact_token_limit.

ForcedLoginMethod

ModeKind

Initial collaboration mode to use when the TUI starts.

MultiAgentMode

Controls the effective multi-agent delegation instructions for a turn. custom means the configured mode hint defines the policy instead of a built-in policy.

Personality

ReasoningSummary

A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model’s reasoning process. See https://platform.openai.com/docs/guides/reasoning?api-mode=responses#reasoning-summaries

SandboxMode

ServiceTier

ShellEnvironmentPolicyFilter

Assigns a shell environment variable pattern to the include-only or exclude set. Includes do not re-add variables removed by another exclude pattern.

ShellEnvironmentPolicyInherit

TrustLevel

Represents the trust level for a project directory. This determines the approval policy and sandbox mode applied.

Verbosity

Controls output length/detail on GPT-5 models via the Responses API. Serialized with lowercase values to match the OpenAI API.

WebSearchContextSize

WebSearchMode

WebSearchUserLocationType

WindowsSandboxLevel

Constants

SERVICE_TIER_DEFAULT_REQUEST_VALUE

Request/config sentinel for explicit standard routing.

TUI_VISIBLE_COLLABORATION_MODES

Type Aliases

EnvironmentVariablePattern