Skip to main content

Interface: AgentOptions

Defined in: packages/agentos/src/api/agent.ts:112

Configuration options for the agent factory function.

Extends BaseAgentConfig with backward-compatible convenience fields. All BaseAgentConfig fields (rag, discovery, permissions, emergent, voice, etc.) are accepted and stored in config but are not actively wired in the lightweight agent — they will be consumed by agency() and the full runtime.

Extends​

  • BaseAgentConfig

Extended by​

Properties​

apiKey?​

optional apiKey: string

Defined in: packages/agentos/src/api/types.ts:1261

Override the provider API key instead of reading from environment variables.

Inherited from​

BaseAgentConfig.apiKey

avatar?​

optional avatar: AvatarConfig

Defined in: packages/agentos/src/api/types.ts:1400

Avatar visual presentation configuration.

Inherited from​

BaseAgentConfig.avatar

baseUrl?​

optional baseUrl: string

Defined in: packages/agentos/src/api/types.ts:1263

Override the provider base URL (useful for local proxies or Ollama).

Inherited from​

BaseAgentConfig.baseUrl

cache?​

optional cache: false | { ttl?: "5m" | "1h"; }

Defined in: packages/agentos/src/api/agent.ts:251

Per-call prompt-cache control forwarded to every generate / stream / session call this agent makes (same contract as GenerateTextOptions.cache): false sends zero cache markers; { ttl: '1h' } re-times the auto markers — including the moving conversation-history tail — onto the 1-hour cache. Set '1h' for agent loops whose steps gap past the 5-minute default cache TTL (multi-minute tool executions between LLM steps), where the default-paced history marker expires between steps and every step re-writes the whole prefix. Unset -> the provider's default marker pacing.

chainOfThought?​

optional chainOfThought: string | boolean

Defined in: packages/agentos/src/api/agent.ts:124

Chain-of-thought reasoning instruction.

  • false — disable CoT injection.
  • true (default for agents) — inject the default CoT instruction when tools are present.
  • string — inject a custom CoT instruction when tools are present.

channels?​

optional channels: Record<string, Record<string, unknown>>

Defined in: packages/agentos/src/api/types.ts:1405

Channel adapter configurations keyed by channel name. Values are channel-specific option objects passed through opaquely.

Inherited from​

BaseAgentConfig.channels

cognitiveMechanisms?​

optional cognitiveMechanisms: CognitiveMechanismsConfig

Defined in: packages/agentos/src/api/types.ts:1450

Cognitive mechanisms config — 8 neuroscience-backed memory mechanisms. All HEXACO-modulated (emotionality, conscientiousness, openness, etc.).

  • Pass {} for sensible defaults (all 8 mechanisms enabled).
  • Omit entirely to disable (zero overhead — no code paths execute).
  • Provide per-mechanism overrides to tune individual parameters.

Requires memory to be enabled (true or a MemoryConfig object). If cognitiveMechanisms is set but memory is disabled, a warning is logged and the mechanisms config is ignored.

See​

Cognitive Mechanisms Docs

Inherited from​

BaseAgentConfig.cognitiveMechanisms

controls?​

optional controls: ResourceControls

Defined in: packages/agentos/src/api/types.ts:1427

Resource limits (tokens, cost, time). agency() and the full runtime enforce every field against the entire run. The lightweight agent() helper forwards two of them per call: maxTotalTokens caps each LLM call's completion output (mapped to maxTokens when no explicit maxTokens is set, NOT the prompt+completion run total) and maxDurationMs bounds each LLM request (mapped to requestTimeout). The remaining fields stay agency()-only.

Inherited from​

BaseAgentConfig.controls

customModelParams?​

optional customModelParams: Record<string, unknown>

Defined in: packages/agentos/src/api/types.ts:1371

Provider-specific TOP-LEVEL request-payload parameters forwarded verbatim on every generate/stream/session call via ModelCompletionOptions.customModelParams. Providers spread these onto the outgoing request body — the escape hatch for params the typed options don't model, e.g. OpenRouter provider-routing preferences:

customModelParams: { provider: { sort: 'throughput' } }

Inherited from​

BaseAgentConfig.customModelParams

dependsOn?​

optional dependsOn: string[]

Defined in: packages/agentos/src/api/types.ts:1434

Names of other agents in the agency that must complete before this agent runs. Used with strategy: 'graph' to build an explicit dependency DAG. Agents with no dependsOn are roots and run first.

Example​

`dependsOn: ['researcher']` — this agent waits for `researcher` to finish.

Inherited from​

BaseAgentConfig.dependsOn

discovery?​

optional discovery: DiscoveryConfig

Defined in: packages/agentos/src/api/types.ts:1382

Runtime capability discovery configuration.

Inherited from​

BaseAgentConfig.discovery

effort?​

optional effort: string

Defined in: packages/agentos/src/api/types.ts:1359

Reasoning-effort control forwarded to every generate/stream/session call. On effort-capable Claude models (Opus 4.5+, Sonnet 4.6, Fable/Mythos 5) the provider sends output_config.effort (low|medium|high|xhigh|max). On OpenAI reasoning models (o-series, GPT-5.x) the provider sends reasoning_effort (chat) / reasoning.effort (Responses), with max clamping to xhigh — OpenAI's ceiling — and a model-aware guard capping xhigh → high on ids not probe-verified for xhigh (gpt-5.5/5.6 families are verified). Independent of thinking; ignored on unsupported models/values. Works per-agent in agency() rosters — each sub-agent may pin its own depth.

Inherited from​

BaseAgentConfig.effort

emergent?​

optional emergent: EmergentConfig

Defined in: packages/agentos/src/api/types.ts:1396

Emergent agent synthesis configuration.

Inherited from​

BaseAgentConfig.emergent

fallbackProviders?​

optional fallbackProviders: FallbackProviderEntry[]

Defined in: packages/agentos/src/api/agent.ts:137

Ordered list of fallback providers to try when the primary provider fails with a retryable error (HTTP 402/429/5xx, network errors).

Defaults to auto-built chain when omitted — fallback is on by default. Pass [] for strict single-provider mode, or supply a custom array to control the chain. Applied to every generate(), stream(), and session.send() / session.stream() call made through this agent.

See​

GenerateTextOptions.fallbackProviders

guardrails?​

optional guardrails: string[] | GuardrailsConfig

Defined in: packages/agentos/src/api/types.ts:1388

Guardrail policy identifiers or structured config.

  • string[] — shorthand; applies to both input and output.
  • GuardrailsConfig — full control with separate input/output lists.

Inherited from​

BaseAgentConfig.guardrails

history?​

optional history: false | Partial<SessionHistoryConfig>

Defined in: packages/agentos/src/api/agent.ts:260

Session conversation-history policy (spec 2026-07-20 §1a/§1c). Sessions maintain a lossless transcript by default — independent of the memory subsystem — bounded past maxTokens (default 120K estimated) by chunk-amortized whole-block eviction. false restores stateless sessions (the pre-0.10 memory: false behavior). Partial objects override individual bounds.

hitl?​

optional hitl: HitlConfig

Defined in: packages/agentos/src/api/types.ts:1394

Human-in-the-loop approval configuration.

Inherited from​

BaseAgentConfig.hitl

hostPolicy?​

optional hostPolicy: HostLLMPolicy

Defined in: packages/agentos/src/api/agent.ts:148

Host-level routing hints forwarded to the high-level generation helpers.

instructions?​

optional instructions: string

Defined in: packages/agentos/src/api/types.ts:1257

Free-form system instructions prepended to the system prompt.

Inherited from​

BaseAgentConfig.instructions

maxSteps?​

optional maxSteps: number

Defined in: packages/agentos/src/api/types.ts:1292

Maximum number of agentic steps (LLM calls) per invocation. Defaults to 5.

Inherited from​

BaseAgentConfig.maxSteps

maxTokens?​

optional maxTokens: number

Defined in: packages/agentos/src/api/types.ts:1325

Upper bound on completion tokens for each LLM call the agent makes. Forwarded to the underlying generateText / streamText call on every generate(), stream(), and session.send() invocation.

Caps tail spend when a model misbehaves and yaps past the intended output size. Omit to use the provider default — AnthropicProvider defaults to 16000 (set 2026-05-17; was 4096), OpenAIProvider defaults to 4096, GeminiProvider defaults to 8192. Set to ~2× the agent's typical response size so normal calls finish naturally and only runaway generations hit the cap.

Example​

// Cap a roleplay agent at 1024 — short turns, fast feedback.
const companion = agent({
  provider: 'anthropic',
  model: 'claude-sonnet-4-6',
  instructions: 'Reply in character. 2-3 sentences.',
  maxTokens: 1024,
});

// Tool-use agent emitting verbose JSON — go big so structured
// output doesn't truncate mid-token. Opus 4.7 supports 32000.
const codegen = agent({
  provider: 'anthropic',
  model: 'claude-opus-4-7',
  tools: { GenerateCode, RunTests, JudgeOutput },
  maxTokens: 16000,
});

Inherited from​

BaseAgentConfig.maxTokens

memory?​

optional memory: boolean | MemoryConfig

Defined in: packages/agentos/src/api/types.ts:1378

Memory configuration.

  • true — enable in-memory conversation history with default settings.
  • false — disable memory; every call is stateless.
  • MemoryConfig — full control over memory subsystems.

Inherited from​

BaseAgentConfig.memory

memoryProvider?​

optional memoryProvider: AgentMemoryProvider

Defined in: packages/agentos/src/api/agent.ts:219

Optional memory provider. When provided, memory auto-wires on all four agent call paths (see AgentMemoryProvider for hook contract).

  • getContext runs before each LLM call; result prepended as a system message.
  • observe runs after each LLM call as fire-and-forget.

memoryProviderOptions?​

optional memoryProviderOptions: MemoryProviderHookOptions

Defined in: packages/agentos/src/api/agent.ts:227

Optional tunables for the automatic memoryProvider hooks. timeoutMs bounds each getContext call before the turn ships without memory (default MEMORY_TIMEOUT_MS, 5000); tokenBudget is forwarded to getContext as the recall ceiling (default DEFAULT_MEMORY_TOKEN_BUDGET, 2000). Both fall back to the historical module constants when omitted.

model?​

optional model: string

Defined in: packages/agentos/src/api/types.ts:1250

Model identifier. Accepted in two formats:

  • Plain model name (e.g. "gpt-4o") when provider is also set. Preferred.
  • "provider:model" combined string (e.g. "openai:gpt-4o").

Inherited from​

BaseAgentConfig.model

name?​

optional name: string

Defined in: packages/agentos/src/api/types.ts:1259

Display name for the agent, injected into the system prompt.

Inherited from​

BaseAgentConfig.name

observability?​

optional observability: ObservabilityConfig

Defined in: packages/agentos/src/api/types.ts:1415

Observability and telemetry configuration.

Inherited from​

BaseAgentConfig.observability

on?​

optional on: AgencyCallbacks

Defined in: packages/agentos/src/api/types.ts:1417

Event callbacks fired at various lifecycle points during the run.

Inherited from​

BaseAgentConfig.on

onAfterGeneration()?​

optional onAfterGeneration: (result) => Promise<void | GenerationHookResult>

Defined in: packages/agentos/src/api/agent.ts:208

Post-generation hook, called after each LLM step.

Parameters​

result​

GenerationHookResult

Returns​

Promise<void | GenerationHookResult>

onBeforeGeneration()?​

optional onBeforeGeneration: (context) => Promise<void | GenerationHookContext>

Defined in: packages/agentos/src/api/agent.ts:206

Pre-generation hook, called before each LLM step.

Parameters​

context​

GenerationHookContext

Returns​

Promise<void | GenerationHookContext>

onBeforeToolExecution()?​

optional onBeforeToolExecution: (info) => Promise<ToolCallHookInfo | null>

Defined in: packages/agentos/src/api/agent.ts:210

Pre-tool-execution hook.

Parameters​

info​

ToolCallHookInfo

Returns​

Promise<ToolCallHookInfo | null>

onFallback()?​

optional onFallback: (error, fallbackProvider) => void

Defined in: packages/agentos/src/api/agent.ts:144

Callback invoked when a fallback provider is about to be tried.

Parameters​

error​

Error

The error that triggered the fallback.

fallbackProvider​

string

The provider identifier being tried next.

Returns​

void

output?​

optional output: unknown

Defined in: packages/agentos/src/api/types.ts:1411

Output schema for structured generation. Accepts a Zod schema at runtime; typed as unknown here to avoid a hard dependency on the zod package in the types layer.

Inherited from​

BaseAgentConfig.output

permissions?​

optional permissions: PermissionsConfig

Defined in: packages/agentos/src/api/types.ts:1392

Fine-grained tool and resource permission overrides.

Inherited from​

BaseAgentConfig.permissions

personality?​

optional personality: Partial<{ agreeableness: number; conscientiousness: number; emotionality: number; extraversion: number; honesty: number; honesty_humility: number; honestyHumility: number; openness: number; opennessToExperience: number; }>

Defined in: packages/agentos/src/api/types.ts:1271

HEXACO-inspired personality trait overrides (0–1 scale). Encoded as a human-readable trait string appended to the system prompt. The SOUL.md spellings honestyHumility / honesty_humility and opennessToExperience are accepted for honesty and openness; when both spellings are given, the canonical key wins.

Inherited from​

BaseAgentConfig.personality

policyTier?​

optional policyTier: "safe" | "standard" | "mature" | "private-adult"

Defined in: packages/agentos/src/api/agent.ts:160

Caller's intended content policy tier, forwarded to every generate() / stream() / session call this agent makes (same contract as GenerateTextOptions.policyTier): on 'mature' / 'private-adult' with no explicit fallbackProviders, the auto-built fallback chain prepends uncensored legs so a content-policy refusal from the primary re-routes to a model that can complete the request, and the model router receives the tier as a routing hint. Unset keeps the availability-only chain and tier-agnostic routing. A per-call policyTier in extra overrides this value.

provenance?​

optional provenance: AgencyProvenanceConfig

Defined in: packages/agentos/src/api/types.ts:1413

Provenance and audit-trail configuration.

Inherited from​

BaseAgentConfig.provenance

provider?​

optional provider: string

Defined in: packages/agentos/src/api/types.ts:1255

Provider name (e.g. "openai", "anthropic", "ollama"). Auto-detected from environment API keys when omitted.

Inherited from​

BaseAgentConfig.provider

rag?​

optional rag: RagConfig

Defined in: packages/agentos/src/api/types.ts:1380

Retrieval-Augmented Generation configuration.

Inherited from​

BaseAgentConfig.rag

responseSchema?​

optional responseSchema: ZodType<unknown, unknown, $ZodTypeInternals<unknown, unknown>>

Defined in: packages/agentos/src/api/agent.ts:204

Optional Zod schema for validating the LLM's structured output.

When provided, the agent's generate() result includes a parsed field with the Zod-validated and typed output. JSON extraction and validation happen automatically in the onAfterGeneration hook. On validation failure, the agent retries internally (up to controls.maxValidationRetries ?? 1).

When omitted, behavior is unchanged — result.parsed is undefined. This is a non-breaking additive change.

Example​

import { z } from 'zod';
const myAgent = agent({
  name: 'Extractor',
  instructions: 'Extract entities as JSON',
  responseSchema: z.object({ entities: z.array(z.string()) }),
});
const result = await myAgent.generate('Find entities in: ...');
console.log(result.parsed?.entities); // string[]

router?​

optional router: IModelRouter

Defined in: packages/agentos/src/api/agent.ts:146

Model router for intelligent provider selection per-call.

routerParams?​

optional routerParams: Partial<ModelRouteParams>

Defined in: packages/agentos/src/api/agent.ts:180

Routing hints passed to the model router's selectModel() call.

Useful for declaring capability requirements up-front so the router can pick a model that actually supports what the agent needs:

agent({
  name: 'World Architect',
  router: policyAwareRouter,
  routerParams: { requiredCapabilities: ['json_mode'] },
  output: WorldIdentitySchema,
});

When omitted, the router receives a minimal default params object (taskHint only, plus function_calling in requiredCapabilities when tools are declared).

security?​

optional security: object

Defined in: packages/agentos/src/api/types.ts:1390

Security tier controlling permitted tools and capabilities.

tier​

tier: SecurityTier

Inherited from​

BaseAgentConfig.security

skills?​

optional skills: SkillEntry[]

Defined in: packages/agentos/src/api/agent.ts:232

Optional skill entries to inject into the system prompt. Skill content is appended to the system prompt as markdown sections.

soul?​

optional soul: string | { content: string; } | { path: string; }

Defined in: packages/agentos/src/api/agent.ts:292

Per-agent identity loaded from a SOUL.md workspace (the OpenClaw / aaronjmars-soul.md convention). Three forms are accepted:

  • Workspace path — points at a directory containing SOUL.md and optional companion files (STYLE.md, IDENTITY.md, AGENTS.md, MEMORY.md, examples/):

    agent({ provider: 'anthropic', soul: '~/.agentos/agents/aria' });

  • Direct file path — points at a single SOUL.md file:

    agent({ provider: 'anthropic', soul: './personas/aria.soul.md' });

  • Inline content — pass the soul markdown directly (useful for tests and ephemeral agents):

    agent({ provider: 'anthropic', soul: { content: SOUL_MARKDOWN_STRING } });

Loading semantics: at agent boot the runtime reads SOUL.md, parses YAML frontmatter into an IPersonaDefinition (HEXACO traits, voice, mood, hardLimits), and injects the markdown body as the FIRST system message — before instructions, chainOfThought, personality, or skills. STYLE.md is appended as a second system message when present.

See​

  • loadSoul in @framers/agentos/cognition/substrate/personas/SoulLoader for the loader implementation and full SOUL.md format spec.
  • https://github.com/aaronjmars/soul.md for the cross-framework convention.

systemBlocks?​

optional systemBlocks: SystemContentBlock[]

Defined in: packages/agentos/src/api/agent.ts:239

Structured system prompt blocks with cache breakpoints. When provided, takes precedence over the assembled string from instructions, name, personality, and skills. Use this for prompt caching support with Anthropic.

thinking?​

optional thinking: false | { budgetTokens: number; }

Defined in: packages/agentos/src/api/types.ts:1346

Extended-thinking switch forwarded to Claude models on every generate() / stream() / session call this agent makes. Any positive budgetTokens turns adaptive thinking on (the number itself is not sent). false turns thinking off with the model's own off shape; Opus 5.5, Fable and Mythos always think. Omitted keeps the model's default: thinking on for Opus 5 and later, Sonnet 5 and later, Fable and Mythos, off for older models. Other providers ignore it.

Example​

const codegen = agent({
  provider: 'anthropic',
  model: 'claude-opus-5',
  tools: { GenerateCode, RunTests, JudgeOutput },
  maxTokens: 24000,
  thinking: { budgetTokens: 8000 },
});

Inherited from​

BaseAgentConfig.thinking

tools?​

optional tools: AdaptableToolInput

Defined in: packages/agentos/src/api/types.ts:1290

Tools available to the agent on every call.

Accepts:

  • a named high-level tool map
  • an ExternalToolRegistry (Record, Map, or iterable)
  • a prompt-only ToolDefinitionForLLM[]

Inherited from​

BaseAgentConfig.tools

usageLedger?​

optional usageLedger: AgentOSUsageLedgerOptions

Defined in: packages/agentos/src/api/agent.ts:117

Top-level usage ledger shorthand. When present, forwarded to observability.usageLedger internally.

verifyCitations?​

optional verifyCitations: VerifyCitationsConfig

Defined in: packages/agentos/src/api/types.ts:1483

Auto-verify citations after every generation.

When set, the agent retrieves sources for each user input, runs generation, then scores each atomic claim in the response against the retrieved sources via CitationVerifier. The resulting VerifiedResponse is attached to the generation result's grounding field — no separate verifier.verify(text, sources) call needed.

Pass a config object with the embedding function and the source retriever the verifier should use:

Example​

const docsAgent = agent({
  provider: 'openai',
  model: 'gpt-4o',
  verifyCitations: {
    embedFn:  (texts) => embeddingManager.embedBatch(texts),
    retrieve: (query) => retriever.search(query),
  },
});

const result = await docsAgent.generate('How do I configure a guardrail?');
console.log(result.text);
console.log(result.grounding?.overallGrounded);
for (const claim of result.grounding?.claims ?? []) {
  if (claim.verdict !== 'supported') console.warn(claim.text);
}

Inherited from​

BaseAgentConfig.verifyCitations

voice?​

optional voice: VoiceConfig

Defined in: packages/agentos/src/api/types.ts:1398

Voice interface configuration.

Inherited from​

BaseAgentConfig.voice