Module config 

Binary-side config module. Pure re-export surface — the real types and helpers live in zeroclaw-config. Everything the binary needs (schema, traits, property helpers) is pulled through here so crate::config::* continues to resolve for callers that predate the crate split.

Modules

migration

providers

schema

Configuration schema — re-exported from zeroclaw-config.

traits

Structs

Ai21ModelProviderConfig

AihubmixModelProviderConfig

AliasedAgentConfig

Configuration for an aliased agent. Each [agents.<alias>] TOML block deserializes into one of these. The DelegateTool looks up entries here to dispatch a subtask to a named sibling agent.

AnthropicModelProviderConfig

Anthropic model model_provider config. No family-specific extras yet — typed slot reserved for future Anthropic-only knobs (cache_control, beta headers) so they land cleanly without another schema rework.

AnyscaleModelProviderConfig

AssemblyAiSttConfig

AssemblyAI STT model_provider configuration ([transcription.assemblyai]).

AstraiModelProviderConfig

AuditConfig

Audit logging configuration

AvianModelProviderConfig

AzureModelProviderConfig

Azure OpenAI model model_provider config. Carries the Azure-specific connection fields (resource, deployment, api_version) — the URI template substitutes {resource} and {deployment} at runtime. Operators can still override the entire endpoint via base.uri.

BackupConfig

Backup tool configuration ([backup] section).

BaichuanModelProviderConfig

BasetenModelProviderConfig

BedrockModelProviderConfig

AWS Bedrock model model_provider config. Carries the AWS region (the URI template substitutes {region} from this field). Bedrock auth is SigV4 — credentials come from the standard AWS credential chain (env vars, instance metadata, profile), not from api_key.

BrowserComputerUseConfig

Computer-use sidecar configuration ([browser.computer_use] section).

BrowserConfig

Browser automation configuration ([browser] section).

BuiltinHooksConfig

CerebrasModelProviderConfig

ChannelsConfig

Top-level channel configurations ([channels] section).

ClassificationRule

A single classification rule mapping message patterns to a model hint.

ClaudeCodeConfig

Claude Code CLI tool configuration ([claude_code] section).

ClaudeCodeRunnerConfig

Claude Code task runner configuration ([claude_code_runner] section).

CloudOpsConfig

Controls the read-only cloud transformation analysis tools: IaC review, migration assessment, cost analysis, and architecture review.

CloudflareModelProviderConfig

CodexCliConfig

Codex CLI tool configuration ([codex_cli] section).

CohereModelProviderConfig

ComposioConfig

Composio managed OAuth tools integration ([composio] section).

Config

Top-level ZeroClaw configuration, loaded from config.toml.

ConversationalAiConfig

Conversational AI agent builder configuration ([conversational_ai] section).

CopilotModelProviderConfig

CostConfig

Cost tracking and budget enforcement configuration ([cost] section).

CronJobDecl

A declarative cron job definition ([cron.<alias>]).

CustomModelProviderConfig

DataRetentionConfig

Data retention and purge configuration ([data_retention] section).

DeepgramSttConfig

Deepgram STT model_provider configuration ([transcription.deepgram]).

DeepinfraModelProviderConfig

DeepmystModelProviderConfig

DeepseekModelProviderConfig

DelegateToolConfig

Global delegate tool configuration for default timeout values.

DiscordConfig

Discord bot channel configuration.

DockerRuntimeConfig

Docker runtime configuration ([runtime.docker] section).

DoubaoModelProviderConfig

EmbeddingRouteConfig

Route an embedding hint to a specific model_provider + model.

EstopConfig

Emergency stop configuration.

FireworksModelProviderConfig

FriendliModelProviderConfig

GatewayConfig

Gateway server configuration ([gateway] section).

GeminiCliConfig

Gemini CLI tool configuration ([gemini_cli] section).

GeminiCliModelProviderConfig

GeminiModelProviderConfig

GlmModelProviderConfig

GoogleSttConfig

Google Cloud Speech-to-Text model_provider configuration ([transcription.google]).

GoogleWorkspaceAllowedOperation

Google Workspace CLI (gws) tool configuration ([google_workspace] section).

GoogleWorkspaceConfig

Google Workspace CLI (gws) tool configuration ([google_workspace] section).

GroqModelProviderConfig

HardwareConfig

Wizard-driven hardware configuration for physical world interaction.

HeartbeatConfig

Heartbeat configuration for periodic health pings ([heartbeat] section).

HooksConfig

HttpRequestConfig

HTTP request tool configuration ([http_request] section).

HuggingfaceModelProviderConfig

HunyuanModelProviderConfig

HyperbolicModelProviderConfig

IMessageConfig

iMessage channel configuration (macOS only).

IdentityConfig

Identity format configuration ([identity] section).

ImageGenConfig

Standalone image generation tool configuration ([image_gen]).

ImageProviderDalleConfig

OpenAI DALL-E settings ([linkedin.image.dalle]).

ImageProviderFluxConfig

Flux (fal.ai) image generation settings ([linkedin.image.flux]).

ImageProviderImagenConfig

Google Imagen (Vertex AI) settings ([linkedin.image.imagen]).

ImageProviderStabilityConfig

Stability AI image generation settings ([linkedin.image.stability]).

JiraConfig

Jira integration configuration ([jira]).

KiloCliModelProviderConfig

KnowledgeConfig

Knowledge graph configuration for capturing and reusing expertise.

LarkConfig

Lark/Feishu configuration for messaging integration. Lark is the international version; Feishu is the Chinese version.

LeptonModelProviderConfig

LinkEnricherConfig

Automatic link understanding for inbound channel messages ([link_enricher]).

LinkedInConfig

LinkedIn integration configuration ([linkedin] section).

LinkedInContentConfig

Content strategy configuration for LinkedIn auto-posting ([linkedin.content]).

LinkedInImageConfig

Image generation configuration for LinkedIn posts ([linkedin.image]).

LitellmModelProviderConfig

LlamacppModelProviderConfig

LmstudioModelProviderConfig

LocalWhisperConfig

Local/self-hosted Whisper-compatible STT endpoint ([transcription.local_whisper]).

MatrixConfig

Matrix channel configuration.

McpConfig

External MCP client configuration ([mcp] section).

McpServerConfig

Configuration for a single external MCP server.

MediaPipelineConfig

Automatic media understanding pipeline configuration ([media_pipeline]).

MemoryConfig

Memory backend configuration ([memory] section).

MemoryPolicyConfig

Memory policy configuration ([memory.policy] section).

Microsoft365Config

Microsoft 365 integration via Microsoft Graph API ([microsoft365] section).

MinimaxModelProviderConfig

MistralModelProviderConfig

ModelProviderConfig

Named model_provider profile definition.

ModelRouteConfig

Route a task hint to a specific model_provider + model.

MoonshotModelProviderConfig

Moonshot model model_provider config. The endpoint field is required (no implicit default) — operators must pick a region explicitly. Migration fills it in from collapsed moonshot-cn / moonshot-intl outer keys.

MqttConfig

MQTT channel configuration (SOP listener).

MultimodalConfig

Multimodal (image) handling configuration ([multimodal] section).

NebiusModelProviderConfig

NextcloudTalkConfig

Nextcloud Talk bot configuration (webhook receive + OCS send API).

NodeTransportConfig

Secure transport configuration for inter-node communication ([node_transport]).

NodesConfig

Configuration for the dynamic node discovery system ([nodes]).

NotionConfig

Notion integration configuration ([notion]).

NovitaModelProviderConfig

NscaleModelProviderConfig

NvidiaModelProviderConfig

ObservabilityConfig

Observability backend configuration ([observability] section).

OllamaModelProviderConfig

OpenAIModelProviderConfig

OpenAI model model_provider config. The OpenAI-family extras (wire_api, requires_openai_auth) live on the shared ModelProviderConfig base because they’re consumed by validation and runtime helpers that operate on the base struct without family awareness; this wrapper is a thin typed slot, no extra fields.

OpenAiSttConfig

OpenAI Whisper STT model_provider configuration ([transcription.openai]).

OpenCodeCliConfig

OpenCode CLI tool configuration ([opencode_cli] section).

OpenRouterModelProviderConfig

OpenVpnTunnelConfig

OpenVPN tunnel configuration ([tunnel.openvpn]).

OpencodeModelProviderConfig

OsaurusModelProviderConfig

OtpConfig

Security OTP configuration.

OvhModelProviderConfig

PacingConfig

Pacing controls for slow/local LLM workloads ([pacing] section).

PeripheralBoardConfig

Configuration for a single peripheral board (e.g. STM32, RPi GPIO).

PeripheralsConfig

Peripheral board integration configuration ([peripherals] section).

PerplexityModelProviderConfig

PipelineConfig

Pipeline tool configuration ([pipeline] section).

PluginsConfig

Plugin system configuration.

PostgresStorageConfig

PostgreSQL storage backend ([storage.postgres.<alias>]).

ProjectIntelConfig

Project delivery intelligence configuration ([project_intel] section).

PropFieldInfo

Describes a single property field discovered via #[derive(Configurable)].

ProxyConfig

Proxy configuration for outbound HTTP/HTTPS/SOCKS5 traffic ([proxy] section).

QdrantStorageConfig

Qdrant vector database backend ([storage.qdrant.<alias>]).

QianfanModelProviderConfig

QueryClassificationConfig

Automatic query classification — classifies user messages by keyword/pattern and routes to the appropriate model hint. Disabled by default.

QwenModelProviderConfig

Qwen model model_provider config. Multi-region (endpoint required) and supports both API key and OAuth flows (auth_mode chooses which).

RekaModelProviderConfig

ReliabilityConfig

Reliability and supervision configuration ([reliability] section).

RiskProfileConfig

Named risk/autonomy profile ([risk_profiles.<alias>]).

RuntimeConfig

Runtime adapter configuration ([runtime] section).

SambanovaModelProviderConfig

SandboxConfig

Sandbox configuration for OS-level isolation

SchedulerConfig

Scheduler configuration for periodic task execution ([scheduler] section).

SecretFieldInfo

Describes a single secret field discovered via #[derive(Configurable)].

SecretsConfig

Secrets encryption configuration ([secrets] section).

SecurityConfig

Security configuration for audit logging, OTP, e-stop, IAM/SSO, and WebAuthn.

SecurityOpsConfig

Managed Cybersecurity Service (MCSS) dashboard agent configuration ([security_ops]).

SglangModelProviderConfig

ShellToolConfig

Shell tool configuration ([shell_tool] section).

SiliconflowModelProviderConfig

SkillCreationConfig

Autonomous skill creation configuration ([skills.skill_creation] section).

SkillImprovementConfig

Skill self-improvement configuration ([skills.auto_improve] section).

SkillsConfig

Skills loading configuration ([skills] section).

SlackConfig

Slack bot channel configuration.

SopConfig

Standard Operating Procedures engine configuration ([sop]).

SqliteStorageConfig

SQLite storage backend ([storage.sqlite.<alias>]).

StepfunModelProviderConfig

StorageConfig

Persistent storage configuration ([storage] section).

SyntheticModelProviderConfig

TelegramConfig

Telegram bot channel configuration.

TelnyxModelProviderConfig

TextBrowserConfig

Text browser tool configuration ([text_browser] section).

TogetherModelProviderConfig

ToolFilterGroup

A named group of MCP tool patterns with an activation mode.

TranscriptionConfig

Voice transcription configuration with multi-provider support.

TtsConfig

Text-to-Speech subsystem configuration ([tts]).

TtsProviderConfig

Per-instance TTS model_provider configuration ([tts_providers.<type>.<alias>]).

TunnelConfig

Tunnel configuration for exposing the gateway publicly ([tunnel] section).

VeniceModelProviderConfig

VercelModelProviderConfig

VerifiableIntentConfig

Verifiable Intent (VI) credential verification and issuance ([verifiable_intent] section).

VllmModelProviderConfig

WebFetchConfig

Web fetch tool configuration ([web_fetch] section).

WebSearchConfig

Web search tool configuration ([web_search] section).

WebhookConfig

Webhook channel configuration.

XaiModelProviderConfig

YiModelProviderConfig

ZaiModelProviderConfig

Enums

CronScheduleDecl

Schedule variant for declarative cron jobs.

HardwareTransport

Hardware transport mode.

McpTransport

Transport type for MCP server connections.

OtpMethod

OTP validation strategy.

PropKind

Runtime type classification for config property values.

ProxyScope

Proxy application scope — determines which outbound traffic uses the proxy.

SandboxBackend

Sandbox backend selection

SearchMode

Search strategy for memory recall.

SkillsPromptInjectionMode

Skills loading configuration ([skills] section).

StreamMode

Streaming mode for channels that support progressive message updates.

ToolFilterGroupMode

Determines when a ToolFilterGroup is active.

WhatsAppChatPolicy

Policy for a particular WhatsApp chat type (DMs or groups) when mode = "personal".

WhatsAppWebMode

WhatsApp Web usage mode.

Constants

DEFAULT_GWS_SERVICES

Built-in default service allowlist for the google_workspace tool.

Traits

HasPropKind

Maps Rust types to PropKind at compile time. Scalars have explicit impls; the blanket impl catches everything else as PropKind::Enum.

Functions

apply_channel_proxy_to_builder

Apply an explicit proxy URL to a reqwest::ClientBuilder, returning the modified builder. Used by channels that specify a per-channel proxy_url.

apply_runtime_proxy_to_builder

build_channel_proxy_client

Build an HTTP client for a channel, using an explicit per-channel proxy URL when configured. Falls back to the global runtime proxy when proxy_url is None or empty.

build_channel_proxy_client_with_timeouts

Build an HTTP client for a channel with custom timeouts, using an explicit per-channel proxy URL when configured. Falls back to the global runtime proxy when proxy_url is None or empty.

build_runtime_proxy_client

build_runtime_proxy_client_with_timeouts

enum_variants

Return a comma-separated string of valid enum variant names for display in error messages.

make_prop_field

Build a PropFieldInfo by reading the display value from a serialized TOML table.

route_hashmap_path

For a #[nested] HashMap<String, T> field, parse a get_prop/set_prop path of the form <my_prefix>.<field_name>.<hm_key>.<inner_suffix> and return the HashMap key + the fully-qualified inner name that the value type’s own get_prop / set_prop expects.

runtime_proxy_config

serde_get_prop

Get a property value via serde serialization.

serde_set_prop

Set a property value via serde roundtrip.

set_runtime_proxy_config

ws_connect_with_proxy

Connect a WebSocket through the configured proxy (if any).