Struct AliasedAgentConfig 

pub struct AliasedAgentConfig {

    pub enabled: bool,
    pub channels: Vec<ChannelRef>,
    pub model_provider: ModelProviderRef,
    pub risk_profile: String,
    pub runtime_profile: String,
    pub skill_bundles: Vec<String>,
    pub knowledge_bundles: Vec<String>,
    pub mcp_bundles: Vec<String>,
    pub cron_jobs: Vec<String>,
    pub tts_provider: TtsProviderRef,
    pub transcription_provider: TranscriptionProviderRef,
    pub classifier_provider: ModelProviderRef,
    pub compact_context: bool,
    pub max_tool_iterations: usize,
    pub max_history_messages: usize,
    pub max_context_tokens: usize,
    pub parallel_tools: bool,
    pub tool_dispatcher: String,
    pub strict_tool_parsing: bool,
    pub tool_call_dedup_exempt: Vec<String>,
    pub tool_filter_groups: Vec<ToolFilterGroup>,
    pub max_system_prompt_chars: usize,
    pub thinking: ThinkingConfig,
    pub history_pruning: HistoryPrunerConfig,
    pub precheck: ChannelPrecheckConfig,
    pub context_aware_tools: bool,
    pub eval: EvalConfig,
    pub auto_classify: Option<AutoClassifyConfig>,
    pub context_compression: ContextCompressionConfig,
    pub max_tool_result_chars: usize,
    pub keep_tool_context_turns: usize,
    pub tool_receipts: ToolReceiptsConfig,
    pub workspace: AgentWorkspaceConfig,
    pub memory: AgentMemoryConfig,
    pub identity: IdentityConfig,
}

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.

Fields

enabled: bool

Whether this agent is active. Set false to disable without removing the definition.

channels: Vec<ChannelRef>

Channel aliases this agent handles (e.g. ["telegram.<alias>", "discord.<alias>"]). Each entry is a ChannelRef resolving through [channels.<type>.<alias>]; Config::validate() fails loud on dangling references.

model_provider: ModelProviderRef

Dotted model-provider alias (e.g. "anthropic.<alias>"). Resolves through model_providers.<type>.<alias> at runtime; Config::validate() fails loud on dangling references.

risk_profile: String

Risk profile alias (e.g. "default"). Resolves delegation guardrails at runtime.

runtime_profile: String

Runtime profile alias (e.g. "default"). Resolves agentic/iteration settings.

skill_bundles: Vec<String>

Skill bundle aliases. Each entry resolves to skill_bundles[key].directory at runtime; the agent loads every listed bundle.

knowledge_bundles: Vec<String>

Knowledge bundle aliases. Additive — the agent loads every listed bundle.

mcp_bundles: Vec<String>

MCP bundle aliases. Each entry references mcp_bundles[key], itself a named group of MCP servers; agents pick which bundles to load.

cron_jobs: Vec<String>

Cron job aliases. Each entry references cron[key] — a declarative scheduled job invoked by the scheduler on its configured trigger. When the cron fires, this agent is the actor that executes the job.

tts_provider: TtsProviderRef

TTS provider as a dotted alias reference (<type>.<alias>, e.g. "openai.<alias>"). Resolves through tts_providers.<type>.<alias>. Empty = no TTS for this agent (there is no global default-provider concept; every agent that wants TTS sets its own tts_provider).

transcription_provider: TranscriptionProviderRef

Transcription / STT provider as a dotted alias reference (<type>.<alias>, e.g. "groq.<alias>"). Resolves through transcription_providers.<type>.<alias>. Empty = agent has no transcription preference; channels that ingest voice still need a resolved provider (there is no global default), so an inbound voice flow into an agent with empty transcription_provider errors loudly at the channel boundary.

classifier_provider: ModelProviderRef

Optional override for the per-message LLM reply-intent classifier (classify_channel_reply_intent in zeroclaw-channels). When non-empty, the channel orchestrator routes the “should this message be replied to?” classification call to [providers.models.<type>.<alias>] referenced here, instead of reusing the main agent’s model_provider.

Source of truth for api_key / uri / model / temperature etc. is the referenced [providers.models.<type>.<alias>] entry. This field is a reference only (NEVER a copy) — per AGENTS.md SINGLE SOURCE OF TRUTH.

Empty (Default) = inherit the main agent’s resolved provider+model (preserves pre-PR behavior; backward compatible).

Use case: classification is a cheap REPLY/NO_REPLY decision, doesn’t need a high-end model. Point this at a fast/free small model (e.g. kimi-k2.5, qwen-turbo) while model_provider stays on the expensive answering model (e.g. qwen3.6-plus).

Note: TOML table names cannot contain ., so alias kimi-k2.5 must be written as [providers.models.custom.kimi-k2-5]. The underlying model = "kimi-k2.5" string can still contain dots.

ACP channels (IDE-direct) always reply and skip the classifier entirely — this field has no effect on ACP traffic.

compact_context: bool

When true: bootstrap_max_chars=6000, rag_chunk_limit=2. Use for 13B or smaller models.

max_tool_iterations: usize

Maximum tool-call loop turns per user message. Default: 10. Setting to 0 falls back to the safe default of 10.

max_history_messages: usize

Maximum conversation history messages retained per session. Default: 50.

max_context_tokens: usize

Maximum estimated tokens for conversation history before compaction triggers. Uses ~4 chars/token heuristic. When this threshold is exceeded, older messages are summarized to preserve context while staying within budget. Default: 32000.

parallel_tools: bool

Enable parallel tool execution within a single iteration. Default: false.

tool_dispatcher: String

Tool dispatch strategy (e.g. "auto"). Default: "auto".

strict_tool_parsing: bool

When true, only native provider tool calls are executable. Text fallback parsing remains disabled, so XML/markdown/GLM-looking text is treated as final assistant text.

tool_call_dedup_exempt: Vec<String>

Tools exempt from the within-turn duplicate-call dedup check. Default: [].

tool_filter_groups: Vec<ToolFilterGroup>

Per-turn MCP tool schema filtering groups.

When non-empty, only MCP tools matched by an active group are included in the tool schema sent to the LLM for that turn. Built-in tools always pass through. Default: [] (no filtering — all tools included).

max_system_prompt_chars: usize

Maximum characters for the assembled system prompt. When > 0, the prompt is truncated to this limit after assembly (keeping the top portion which contains identity and safety instructions). 0 means unlimited. Useful for small-context models (e.g. glm-4.5-air ~8K tokens → set to 8000).

thinking: ThinkingConfig

Thinking/reasoning level control. Configures how deeply the model reasons per message. Users can override per-message with /think:<level> directives.

history_pruning: HistoryPrunerConfig

History pruning configuration for token efficiency.

precheck: ChannelPrecheckConfig

Reply-intent precheck configuration for channel messages.

context_aware_tools: bool

Enable context-aware tool filtering (only surface relevant tools per iteration).

eval: EvalConfig

Post-response quality evaluator configuration.

auto_classify: Option<AutoClassifyConfig>

Automatic complexity-based classification fallback.

context_compression: ContextCompressionConfig

Context compression configuration for automatic conversation compaction.

max_tool_result_chars: usize

Maximum characters for a single tool result before truncation. Head (2/3) and tail (1/3) are preserved with a truncation marker in the middle. Set to 0 to disable truncation. Default: 50000.

keep_tool_context_turns: usize

Number of most recent conversation turns whose full tool-call/result messages are preserved in channel conversation history. Older turns keep only the final assistant text. Set to 0 to disable (previous behavior). Default: 2.

tool_receipts: ToolReceiptsConfig

HMAC tool execution receipt configuration.

workspace: AgentWorkspaceConfig

Per-agent workspace block ([agents.<alias>.workspace]). Holds the agent’s filesystem path, cross-agent access allowlist, filesystem-escape boolean, and cross-agent memory allowlist. Default is fully jailed (no cross-agent access). See crate::multi_agent::AgentWorkspaceConfig.

memory: AgentMemoryConfig

Per-agent memory backend selection ([agents.<alias>.memory]). The backend field is locked at agent creation and immutable on subsequent loads. Defaults to Sqlite. See crate::multi_agent::AgentMemoryConfig.

identity: IdentityConfig

Per-agent identity format ([agents.<alias>.identity]). Each agent renders its own IDENTITY.md / SOUL.md inside its per-agent workspace; this block selects the format (OpenClaw or AIEOS) and optional inline/file source for the agent’s identity document.

Implementations

impl AliasedAgentConfig

pub fn configurable_prefix() -> &'static str

Returns the #[prefix] value for this Configurable struct.

pub fn secret_fields(&self) -> Vec<SecretFieldInfo>

Returns metadata about all #[secret] fields on this struct and nested children.

pub fn secret_field_terminals() -> Vec<&'static str>

Static enumeration of every #[secret] field’s terminal name (snake_case, matching the on-disk TOML key) reachable from this type via #[nested] traversal. Unlike secret_fields(), this requires no instance — the per-struct codegen literals are joined at call time with recursive calls into the inner types’ own secret_field_terminals().

Used by the migration crate’s raw-TOML encrypt walker as the secret-key allowlist. prop_fields()-derived allowlists skip compound (non-Vec) #[secret] fields, so this method is the authoritative source.

pub fn encrypt_secrets(&mut self, store: &SecretStore) -> Result<(), Error>

Encrypt all secret fields in place using the provided store.

pub fn decrypt_secrets(&mut self, store: &SecretStore) -> Result<(), Error>

Decrypt all secret fields in place using the provided store.

pub fn set_secret(&mut self, name: &str, value: String) -> Result<(), Error>

Set a secret field by its full dotted name, dispatching to nested children.

pub fn prop_fields(&self) -> Vec<PropFieldInfo>

Returns metadata about all property fields on this struct and nested children.

pub fn get_prop(&self, name: &str) -> Result<String, Error>

Get a property value by its full dotted name, returning it as a display string.

pub fn set_prop(&mut self, name: &str, value_str: &str) -> Result<(), Error>

Set a property value by its full dotted name, parsing from string.

pub fn prop_is_secret(name: &str) -> bool

Check if a property name refers to a secret field (static, no instance needed).

pub fn init_defaults(&mut self, prefix: Option<&str>) -> Vec<&'static str>

Instantiate None nested sections whose prefix matches. Returns the prefixes that were initialized.

pub fn map_key_sections() -> Vec<MapKeySection>

Enumerate every map-keyed (HashMap<String, T>) and list-shaped (Vec<T>) section discoverable from this Configurable’s tree. The dashboard / CLI consume this to surface “+ Add” affordances without hardcoding the section list.

pub fn nested_section_help(name: &str) -> Option<&'static str>

Help blurb for a #[nested] field on this struct, sourced from the field-level /// docstring. Returns None for unknown names so callers can fall through to a different lookup.

pub fn get_map_keys(&self, section_path: &str) -> Option<Vec<String>>

Return the current alias keys at section_path, or None if the path doesn’t resolve to a map-keyed section in this tree.

pub fn nested_option_entries(&self) -> Vec<NestedOptionEntry>

Snapshot of every #[nested] Option<T> field on this struct as (field_name, is_some) tuples, in declaration order.

field_name is the raw Rust ident (snake_case) — consumers can map to display names via their own table. The schema is the single source of truth: adding a new pub foo: Option<FooConfig> field with #[nested] surfaces here without touching any caller.

pub fn create_map_key( &mut self, section_path: &str, map_key: &str, ) -> Result<bool, String>

Insert a default-valued entry under a map-keyed section, or append to a list-shaped one, with map_key as the new entry’s natural identifier (HashMap key for Map sections; identifier field for List sections).

Returns Ok(true) if a new entry was created, Ok(false) if the entry already existed (idempotent), or Err(reason) if the section path doesn’t resolve to a Map/List in this tree.

pub fn delete_map_key( &mut self, section_path: &str, map_key: &str, ) -> Result<bool, String>

Remove the entry identified by map_key from the map-keyed section at section_path.

Returns Ok(true) if the entry existed and was removed, Ok(false) if it didn’t exist, or Err(reason) if the section path doesn’t resolve.

pub fn rename_map_key( &mut self, section_path: &str, map_key: &str, new_key: &str, ) -> Result<bool, String>

Rename map_key to new_key within the map-keyed section at section_path, preserving the entry’s value.

Returns Ok(true) if renamed, Ok(false) if map_key didn’t exist, or Err(reason) if new_key already exists or the section path doesn’t resolve.

impl AliasedAgentConfig

pub fn is_dispatchable(&self) -> bool

True when this agent has the bindings required to dispatch a turn: enabled, non-empty model_provider, risk_profile, and runtime_profile. Config::validate() emits the per-field errors that, when all passed, mean this returns true.

Trait Implementations

impl Clone for AliasedAgentConfig

fn clone(&self) -> AliasedAgentConfig

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for AliasedAgentConfig

fn fmt(&self, f: &mut Formatter<'_>) -> Result<(), Error>

Formats the value using the given formatter.

impl Default for AliasedAgentConfig

fn default() -> AliasedAgentConfig

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for AliasedAgentConfig

fn deserialize<__D>( __deserializer: __D, ) -> Result<AliasedAgentConfig, <__D as Deserializer<'de>>::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl JsonSchema for AliasedAgentConfig

fn schema_name() -> Cow<'static, str>

The name of the generated JSON Schema.

fn schema_id() -> Cow<'static, str>

Returns a string that uniquely identifies the schema produced by this type.

fn json_schema(generator: &mut SchemaGenerator) -> Schema

Generates a JSON Schema for this type.

fn inline_schema() -> bool

Whether JSON Schemas generated for this type should be included directly in parent schemas, rather than being re-used where possible using the $ref keyword.

impl MaskSecrets for AliasedAgentConfig

fn mask_secrets(&mut self)

fn restore_secrets_from(&mut self, current: &AliasedAgentConfig)

impl Serialize for AliasedAgentConfig

fn serialize<__S>( &self, __serializer: __S, ) -> Result<<__S as Serializer>::Ok, <__S as Serializer>::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.