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();
}

Table of contents

Properties

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

Methods

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

Properties

inputMessages

• inputMessages: Message[] = []

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

Defined in

genai/llm.ts:78

---

model

• Readonly model: string

Defined in

genai/llm.ts:98

---

outputMessages

• outputMessages: Message[] = []

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

Defined in

genai/llm.ts:83

---

providerName

• Readonly providerName: string

Defined in

genai/llm.ts:99

---

reasoning

• Optional reasoning: Reasoning

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

Defined in

genai/llm.ts:90

---

usage

• usage: Usage = {}

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

Defined in

genai/llm.ts:85

Methods

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

genai/llm.ts:168

---

attachMediaUrl

▸ attachMediaUrl(url, opts): this

Convenience for attachMedia({uri, modality}).

Parameters

Name	Type
url	string
opts	Object
opts.modality	Modality

Returns

this

Defined in

genai/llm.ts:186

---

end

▸ end(opts?): void

Flush accumulated state to the span and close it. Idempotent. Pass error to mark the span as failed.

Parameters

Name	Type
opts?	Object
opts.error?	Error

Returns

void

Defined in

genai/llm.ts:246

---

output

▸ output(content): this

Append an assistant message to the response.

Parameters

Name	Type
content	string

Returns

this

Defined in

genai/llm.ts:141

---

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

genai/llm.ts:197

---

startSubagent

▸ startSubagent(opts): SubAgent

Start a child SubAgent span nested under this LLM.

Parameters

Name	Type
opts	SubAgentInit

Returns

SubAgent

Defined in

genai/llm.ts:230

---

startTool

▸ startTool(opts): Tool

Start a child Tool span nested under this LLM.

Parameters

Name	Type
opts	ToolInit

Returns

Tool

Defined in

genai/llm.ts:221

---

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

genai/llm.ts:153

---

create

▸ create(opts): LLM

Parameters

Name	Type
opts	LLMInit & ChildSpanContext

Returns

LLM

Defined in

genai/llm.ts:102