Adaptive#

Generated from crates/node/adaptive.d.ts via sphinx-js.

ComponentSpec#

Wrap adaptive config as a top-level component.

Produces the plugin component entry that can be inserted directly into plugin.defaultConfig().components. Kind: function

Parameters#

  • config Config: Adaptive component configuration document.

  • options { enabled?: boolean; }: Optional component-level flags.

Returns#

  • ComponentSpec: A plugin component spec for the adaptive plugin.

Remarks#

  • Setting options.enabled = false keeps the config in the plugin document for validation while skipping runtime activation.

acgConfig#

Create adaptive cache-governor settings with defaults applied.

Merges caller-supplied overrides onto the ACG config shape used by the adaptive plugin’s LLM execution intercept. Kind: function

Parameters#

  • config AcgConfig: Partial ACG settings to override.

Returns#

  • AcgConfig: A normalized adaptive cache-governor config object.

Remarks#

  • Nested stability_thresholds values are defaulted individually so callers can override only the thresholds they need.

toolParallelismConfig#

Create adaptive tool-parallelism settings with defaults applied.

Merges caller-supplied overrides onto the scheduler config shape used by the adaptive plugin’s tool parallelism component. Kind: function

Parameters#

  • config ToolParallelismConfig: Partial tool scheduling settings to override.

Returns#

  • ToolParallelismConfig: A normalized tool-parallelism config object.

Remarks#

  • The default mode is observe_only, so recommendations are produced without changing execution behavior unless the caller opts in.

adaptiveHintsConfig#

Create adaptive hint-injection settings with defaults applied.

Merges caller-supplied overrides onto the default config used by the adaptive hints injector. Kind: function

Parameters#

  • config AdaptiveHintsConfig: Partial adaptive hints settings to override.

Returns#

  • AdaptiveHintsConfig: A normalized adaptive hints config object.

Remarks#

  • By default the injector runs at priority 100, preserves the rest of the chain, and writes hints to nvext.agent_hints.

telemetryConfig#

Create adaptive telemetry settings with runtime defaults applied.

Merges caller-supplied overrides onto the built-in telemetry config shape used by the adaptive plugin. Kind: function

Parameters#

  • config TelemetryConfig: Partial telemetry settings to override.

Returns#

  • TelemetryConfig: A normalized adaptive telemetry config object.

Remarks#

  • An empty learners array is supplied by default so callers can append learner names without checking for initialization first.

redisBackend#

Create a Redis-backed adaptive state backend spec.

Produces the backend descriptor expected by the adaptive plugin when state should be shared or persisted through Redis. Kind: function

Parameters#

  • url string: Redis connection URL for the backend.

  • keyPrefix string: Prefix applied to Redis keys.

Returns#

  • BackendSpec: An adaptive backend spec using Redis storage.

Remarks#

  • The default key prefix namespaces runtime records under nemo_flow: unless a different prefix is supplied.

inMemoryBackend#

Create an in-memory adaptive state backend spec.

Produces the backend descriptor for ephemeral adaptive state stored inside the current process rather than an external datastore. Kind: function

Returns#

  • BackendSpec: An adaptive backend spec using in-memory storage.

Remarks#

  • This backend does not persist state across process restarts.

defaultConfig#

Create a default adaptive component config.

Returns the minimal top-level adaptive config shape with version = 1 so callers can add state, telemetry, and scheduler settings incrementally. Kind: function

Returns#

  • Config: A new adaptive config object.

Remarks#

  • The returned object is detached from runtime state until it is wrapped with ComponentSpec and activated through the plugin system.

ADAPTIVE_PLUGIN_KIND#

No description available.

Type: "adaptive"

ComponentSpec#

Top-level adaptive component wrapper with fixed kind adaptive. Kind: interface

Members#

  • kind "adaptive"

  • enabled? boolean

  • config Config

Config#

Canonical config object for the top-level adaptive component. Kind: interface

Members#

  • version? number

  • agent_id? string

  • state? StateConfig

  • telemetry? TelemetryConfig

  • adaptive_hints? AdaptiveHintsConfig

  • tool_parallelism? ToolParallelismConfig

  • acg? AcgConfig

  • policy? ConfigPolicy

AcgConfig#

Adaptive cache-governor settings. Kind: interface

Members#

  • provider? string

  • observation_window? number

  • priority? number

  • stability_thresholds? AcgStabilityThresholds

AcgStabilityThresholds#

ACG prompt-stability classification thresholds. Kind: interface

Members#

  • stable_threshold? number

  • semi_stable_threshold? number

  • min_observations_for_full_confidence? number

ToolParallelismConfig#

Built-in adaptive tool scheduling settings. Kind: interface

Members#

  • priority? number

  • mode? string

AdaptiveHintsConfig#

Built-in adaptive hints injection settings. Kind: interface

Members#

  • priority? number

  • break_chain? boolean

  • inject_header? boolean

  • inject_body_path? string

TelemetryConfig#

Built-in adaptive telemetry settings. Kind: interface

Members#

  • subscriber_name? string

  • learners? string[]

StateConfig#

Adaptive state configuration. Kind: interface

Members#

  • backend BackendSpec

BackendSpec#

Adaptive state backend selection. Kind: interface

Members#

  • kind string

  • config? Record<string, Json>

ConfigReport#

No description available.

Alias Of: ConfigReport

ConfigDiagnostic#

No description available.

Alias Of: ConfigDiagnostic

ConfigPolicy#

No description available.

Alias Of: ConfigPolicy

Json#

No description available.

Alias Of: any