Skip to main content

Interface: EmergentConfig

Defined in: packages/agentos/src/cognition/emergent/types.ts:957

Configuration options for the Emergent Capability Engine.

All fields have sensible defaults defined in DEFAULT_EMERGENT_CONFIG. Pass a partial object to override only the fields you need.

Properties​

allowSandboxTools​

allowSandboxTools: boolean

Defined in: packages/agentos/src/cognition/emergent/types.ts:991

Whether sandboxed code tools may be forged at all.

When false, agents may still create compose-mode tools from existing registered tools, but any forge request using implementation.mode: 'sandbox' is rejected before validation or execution.

This is intentionally disabled by default because sandboxed code carries higher review and persistence risk than composing tools that are already registered.

Default​

false

audit?​

optional audit: EmergentAuditConfig

Defined in: packages/agentos/src/cognition/emergent/types.ts:1091

Effect records under a ceiling. Ignored without one.


capabilities?​

optional capabilities: ForgedCapabilities

Defined in: packages/agentos/src/cognition/emergent/types.ts:1088

The ceiling for code-forged tools (see ForgedCapabilities). Absent: the legacy path, where a forged tool takes the APIs it asks for, unscoped. Validated at engine construction; each failure names its key.


compose?​

optional compose: object

Defined in: packages/agentos/src/cognition/emergent/types.ts:1081

Which tools with side effects a composition or a workflow may chain as a step. A tool that declares hasSideEffects: false is chained freely; one that declares true only when its name is listed here; one that declares nothing is never chained. A tool named launch_agency is never chained, whatever it declares and whether or not it is listed here: a team is launched from a turn. The list is read when a step is checked (at forge, at load, at promotion and on every run), not at construction.

sideEffectingTools?​

optional sideEffectingTools: string[]

Default​

{ sideEffectingTools: [] }

effectPolicy?​

optional effectPolicy: EffectPolicy

Defined in: packages/agentos/src/cognition/emergent/types.ts:1102

Called for every write, delete and state-changing request; see EffectPolicy.


enabled​

enabled: boolean

Defined in: packages/agentos/src/cognition/emergent/types.ts:963

Master switch. When false, all forge / promote / execute requests are rejected immediately with a "emergent capabilities disabled" error.

Default​

false

executor?​

optional executor: ForgedCodeExecutor

Defined in: packages/agentos/src/cognition/emergent/types.ts:1110

What runs forged code in the forge the engine builds. Absent: the in-process executor (isolates: false). A host that passes its own sandboxForge brings that forge's executor; passing one beside a different executor fails construction with executor_conflict.


judgeModel​

judgeModel: string

Defined in: packages/agentos/src/cognition/emergent/types.ts:1053

Model ID used by the single LLM judge at forge time (CreationVerdict). Should be a fast, cost-efficient model — correctness is handled by test cases.

Default​

"gpt-4o-mini"

maxAgentTools​

maxAgentTools: number

Defined in: packages/agentos/src/cognition/emergent/types.ts:977

Maximum number of agent-scoped emergent tools persisted per agent. Promotion from 'session' to 'agent' is blocked when this limit is reached.

Default​

50

maxSessionTools​

maxSessionTools: number

Defined in: packages/agentos/src/cognition/emergent/types.ts:970

Maximum number of session-scoped emergent tools an agent may hold at once. Forge requests beyond this limit are rejected until older tools are evicted.

Default​

10

persistSandboxSource​

persistSandboxSource: boolean

Defined in: packages/agentos/src/cognition/emergent/types.ts:1012

Whether sandbox source code should be persisted at rest.

When false, sandbox tools run in memory for the active process, and a fresh forge's row receives redacted metadata instead of raw source code. This reduces the blast radius of runtime-forged code while preserving audit visibility and non-source tool metadata. A rewrite of a row that already holds a source, stored by a host or while this option was on, keeps that source: turning the option off removes nothing, and a host deletes stored source itself.

Persisting raw sandbox source should be an explicit opt-in for trusted environments that need restart-time rehydration of sandbox tools.

A forge's trace is apart from this option: a host that stores a trace stores the forged code it holds.

Default​

false

promotionJudgeModel​

promotionJudgeModel: string

Defined in: packages/agentos/src/cognition/emergent/types.ts:1060

Model ID used by both reviewers in the multi-reviewer promotion panel (PromotionVerdict). Should be a more capable model than judgeModel.

Default​

"gpt-4o"

promotionThreshold​

promotionThreshold: object

Defined in: packages/agentos/src/cognition/emergent/types.ts:1033

Thresholds that must be met before a tool is eligible for tier promotion.

confidence​

confidence: number

Minimum aggregate confidence score (from usage stats) before promotion. In the range [0, 1].

Default​
0.8

uses​

uses: number

Minimum total invocation count before promotion is considered.

Default​
5

protectedPaths?​

optional protectedPaths: string[]

Defined in: packages/agentos/src/cognition/emergent/types.ts:1099

Paths no fs.write or fs.delete root may hold or lie inside, beside the library's own directory, node_modules and the entry script's directory. The library cannot find a host's own code and data: list its source, build output, data directories and a file database here.


sandboxMemoryMB​

sandboxMemoryMB: number

Defined in: packages/agentos/src/cognition/emergent/types.ts:1021

Memory budget in megabytes for each sandboxed tool execution. The in-process executor reports a heap delta and does not enforce it; QuickJSExecutor stops the guest at it (never below 16 MiB). Passed as SandboxExecutionRequest.memoryMB.

Default​

128

sandboxTimeoutMs​

sandboxTimeoutMs: number

Defined in: packages/agentos/src/cognition/emergent/types.ts:1028

Wall-clock timeout in milliseconds for each sandboxed tool execution. Passed as SandboxExecutionRequest.timeoutMs.

Default​

5000

selfImprovement?​

optional selfImprovement: SelfImprovementConfig

Defined in: packages/agentos/src/cognition/emergent/types.ts:1069

Self-improvement configuration for bounded autonomous personality mutation, skill management, workflow composition, and self-evaluation.

When omitted or undefined, self-improvement tools are not registered.

Default​

undefined (disabled)