@nhtio/adk/batteries/llm/litert_lm/types

Types for the LiteRT-LM adapter — options, engine/conversation aliases, and the LiteRT wire shapes re-exported from @litert-lm/core.

Remarks

The published @litert-lm/core JS guide lags the library. The shapes below mirror the installed package's type declarations (the source of truth), which expose tool use, channels ("thinking"), sampler controls, and multimodality that the public docs omit. Verify against the installed .d.ts when upgrading — the dependency is young and volatile.

Interfaces

Interface	Description
LiteRtLmAdapterOptions	Configuration for the in-browser LiteRT-LM adapter.
LiteRtSamplerParametersOption	Sampler-parameters option shape (the type field accepts the numeric SamplerType value).

Type Aliases

Type Alias	Description
Backend	Inference-backend enum value: CPU, GPU, etc.
CreateLiteRtLmEngine	Factory that loads a .litertlm model and resolves a ready-to-use LiteRtLmEngine.
LiteRtConversationConfig	Configuration for an LiteRtLmConversation.
LiteRtEngineSettings	Engine-construction settings ({ model, backend?, mainExecutorSettings? }).
LiteRtLlmExecutorSettings	Per-executor settings (context length, backend config, sampler backend).
LiteRtLmChatEngine	Alias of LiteRtLmEngine.
LiteRtLmConversation	A live LiteRT conversation created from an engine for one dispatch.
LiteRtLmDescriptionLike	The description envelope a joi schema produces, consumed by the JSON-schema converter.
LiteRtLmEngine	The LiteRT-LM engine instance the adapter drives.
LiteRtLmInitProgressReport	Progress report emitted while a LiteRT model loads. Provider-opaque; passed through verbatim.
LiteRtLmJsonSchema	The JSON-schema-shaped value used for a tool's parameters field (re-export for convenience).
LiteRtMessage	A message in a LiteRT conversation: { role, content?, channels?, tool_calls? }.
LiteRtMessageContentItem	An item in a message's content array ({ type, text?, path?, tool_response? }).
LiteRtMessageLike	A string or LiteRtMessage.
LiteRtPreface	Initial messages, tools, and context the conversation begins with.
LiteRtSamplerParameters	Sampler configuration ({ type, k, p, temperature, seed }).
LiteRtSessionConfig	Per-session generation configuration (sampler, modality flags, output limits).
LiteRtTool	A tool definition exposed to the model ({ name, description?, parameters? }).
LiteRtToolCall	A tool call predicted by the model ({ type, function: { name, arguments } }).
LiteRtToolCallFunction	The function payload of a LiteRtToolCall ({ name, arguments: object }).
LiteRtToolParameters	Parameters for a LiteRtTool, following JSON Schema.
LiteRtToolResponseValue	A tool response value fed back to the model.
SamplerType	Sampler-type enum value: TOP_K, TOP_P, GREEDY.

References

DescriptionLike

Re-exports DescriptionLike

---

JsonSchema

Re-exports JsonSchema

---

LiteRtLmBucketOrder

Renames and re-exports ChatCompletionsBucketOrder

---

LiteRtLmHelpers

Renames and re-exports ChatCompletionsHelpers

---

UnsupportedMediaPolicy

Re-exports UnsupportedMediaPolicy