Class: LLM

TypeScript SDK reference

weave / LLM

An LLM call. Emits a chat span with gen_ai.* attributes.

Created by weave.startLLM() (or turn.startLLM()) and terminated with end(). Only one LLM may be active in an async context at a time; nest tool/subagent calls under it via startTool / startSubagent.

Populate inputMessages / outputMessages / usage / reasoning directly, or via the helper functions (output, think, attachMedia, record).

All recorded data is flushed to the span at end().

Example

const llm = weave.startLLM({model: 'gpt-4o-mini', providerName: 'openai'});
try {
  llm.inputMessages = [{role: 'user', content: prompt}];
  const resp = await openai.chat.completions.create({...});
  llm.output(resp.choices[0].message.content ?? '');
  llm.record({usage: {inputTokens: resp.usage?.prompt_tokens}});
} finally {
  llm.end();
}

Hierarchy

• SpanBase

  ↳ LLM

Table of contents

Properties

• inputMessages
• model
• outputMessages
• providerName
• reasoning
• usage

Methods

• addEvent
• attachMedia
• attachMediaUrl
• end
• output
• record
• setAttributes
• startSubagent
• startTool
• think
• create

Properties

inputMessages

• inputMessages: Message[] = []

Input messages sent to the model. Flushed to gen_ai.input.messages on end().

Defined in

src/genai/llm.ts:79

---

model

• Readonly model: string

Defined in

src/genai/llm.ts:97

---

outputMessages

• outputMessages: Message[] = []

Assistant messages returned by the model. Flushed to gen_ai.output.messages on end().

Defined in

src/genai/llm.ts:84

---

providerName

• Readonly providerName: string

Defined in

src/genai/llm.ts:98

---

reasoning

• Optional reasoning: Reasoning

Chain-of-thought content. Folded into the last assistant message as a ReasoningPart at serialization time.

Defined in

src/genai/llm.ts:91

---

usage

• usage: Usage = {}

Token counts and cache stats. Flushed to gen_ai.usage.* on end().

Defined in

src/genai/llm.ts:86

Methods

addEvent

▸ addEvent(name, attributes?, startTime?): this

Add a named event to the span. Useful for marking non-span moments such as context compaction, tool-loop detection, or guardrail trips. Warns and no-ops after end(). Mirrors OTel Span.addEvent.

Parameters

Name	Type
name	string
attributes?	Attributes
startTime?	TimeInput

Returns

this

Example

span.addEvent('context_compacted', {removedMessages: 12});

Inherited from

SpanBase.addEvent

Defined in

src/genai/spanBase.ts:77

---

attachMedia

▸ attachMedia(opts): this

Attach a media part to the last input message. Pick exactly one of content (inline base64 bytes), uri (URI reference), or fileId (pre-uploaded file id).

Parameters

Name	Type
opts	AttachMediaOpts

Returns

this

Defined in

src/genai/llm.ts:170

---

attachMediaUrl

▸ attachMediaUrl(url, opts): this

Convenience for attachMedia({uri, modality}).

Parameters

Name	Type
url	string
opts	Object
opts.modality	Modality

Returns

this

Defined in

src/genai/llm.ts:188

---

end

▸ end(opts?): void

Flush accumulated state and close the span. Idempotent. Pass error to mark failed; pass endTime to backdate the close.

Parameters

Name	Type
opts?	SpanEndOptions

Returns

void

Defined in

src/genai/llm.ts:245

---

output

▸ output(content): this

Append an assistant message to the response.

Parameters

Name	Type
content	string

Returns

this

Defined in

src/genai/llm.ts:143

---

record

▸ record(opts): this

Bulk-set any subset of the mutable fields. Replaces (does not merge). Useful for assigning everything at once after a provider call returns.

Parameters

Name	Type
opts	LLMRecordOpts

Returns

this

Defined in

src/genai/llm.ts:199

---

setAttributes

▸ setAttributes(attributes): this

Set multiple attributes on the span at once. Warns and no-ops after end(). Mirrors OTel Span.setAttributes (and the Python SDK’s set_attributes).

Parameters

Name	Type
attributes	Attributes

Returns

this

Example

span.setAttributes({'weave.tag': 'prod', 'gen_ai.response.id': id});

Inherited from

SpanBase.setAttributes

Defined in

src/genai/spanBase.ts:63

---

startSubagent

▸ startSubagent(opts): SubAgent

Start a child SubAgent span nested under this LLM.

Parameters

Name	Type
opts	SubAgentInit

Returns

SubAgent

Defined in

src/genai/llm.ts:232

---

startTool

▸ startTool(opts): Tool

Start a child Tool span nested under this LLM.

Parameters

Name	Type
opts	ToolInit

Returns

Tool

Defined in

src/genai/llm.ts:223

---

think

▸ think(content): this

Set or extend the model’s reasoning/chain-of-thought content. Accumulates into this.reasoning.content. Folded into the last assistant message as a ReasoningPart at serialization time, matching the Python SDK’s on-the-wire shape.

Parameters

Name	Type
content	string

Returns

this

Defined in

src/genai/llm.ts:155

---

create

▸ create(opts): LLM

Parameters

Name	Type
opts	LLMInit & ChildSpanContext

Returns

LLM

Defined in

src/genai/llm.ts:103