Skip to main content
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  = weave.startLLM({: 'gpt-4o-mini', : 'openai'});

try {
  .inputMessages = [{: 'user', : prompt}];
  const  = await openai.chat.completions.create({...});
  .output(.choices[0].message.content ?? '');
  .record({: {: .usage?.prompt_tokens}});
} finally {
  .end();
}
Example 
const  = weave.startLLM({
  : 'gpt-4o-mini',
  : 'openai',
  : ['You are a helpful weather bot.'],
  : new ('2026-05-29T10:00:00.000Z'),
});

try {
  // ... call the LLM, populate llm.outputMessages / usage ...
} finally {
  .end();
}

​
Hierarchy

  • SpanBase ↳ LLM

​
Table of contents

​
Properties

​
Methods

​
Properties

​
inputMessages

• inputMessages: Message[] = [] Input messages sent to the model. Flushed to gen_ai.input.messages on end().

​
Defined in

src/genai/llm.ts:93

​
model

• Readonly model: string

​
Defined in

src/genai/llm.ts:117

​
outputMessages

• outputMessages: Message[] = [] Assistant messages returned by the model. Flushed to gen_ai.output.messages on end().

​
Defined in

src/genai/llm.ts:98

​
providerName

• Readonly providerName: string

​
Defined in

src/genai/llm.ts:118

​
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:105

​
usage

• usage: Usage = {} Token counts and cache stats. Flushed to gen_ai.usage.* on end().

​
Defined in

src/genai/llm.ts:100

​
Methods

​
addEvent

Deprecated. Record this data via setAttributes instead. OpenTelemetry is phasing out the Span Event API (Span.addEvent). This method still works and existing span-event data stays valid. See https://opentelemetry.io/blog/2026/deprecating-span-events/Example
span.addEvent('context_compacted', {: 12});
▸ 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

NameType
namestring
attributes?Attributes
startTime?TimeInput

​
Returns

this

​
Inherited from

SpanBase.addEvent

​
Defined in

src/genai/spanBase.ts:82

​
attachMedia

▸ attachMedia(opts): this Stage a media attachment for the LLM call. Pick exactly one of content (inline base64 bytes), uri (URI reference), or fileId (pre-uploaded file id). The attachment is glued onto the last user message in inputMessages on end().

​
Parameters

NameType
optsAttachMediaOpts

​
Returns

this

​
Defined in

src/genai/llm.ts:183

​
attachMediaUrl

▸ attachMediaUrl(url, opts): this Convenience for attachMedia({uri, modality}).

​
Parameters

NameType
urlstring
optsObject
opts.modalityModality

​
Returns

this

​
Defined in

src/genai/llm.ts:192

​
end

▸ end(opts?): void Flush accumulated state and close the span. Idempotent. Pass error to mark failed; pass endTime to backdate the close.

​
Parameters

NameType
opts?SpanEndOptions

​
Returns

void

​
Defined in

src/genai/llm.ts:274

​
output

▸ output(content): this Append an assistant message to the response.

​
Parameters

NameType
contentstring

​
Returns

this

​
Defined in

src/genai/llm.ts:155

​
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

NameType
optsObject
opts.finishReasons?string[]
opts.inputMessages?Message[]
opts.mediaAttachments?AttachMediaOpts[]
opts.outputMessages?Message[]
opts.outputType?string
opts.reasoning?Reasoning
opts.responseId?string
opts.responseModel?string
opts.usage?Usage

​
Returns

this

​
Defined in

src/genai/llm.ts:203

​
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

NameType
attributesAttributes

​
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

NameType
optsSubAgentInit

​
Returns

SubAgent

​
Defined in

src/genai/llm.ts:261

​
startTool

▸ startTool(opts): Tool Start a child Tool span nested under this LLM.

​
Parameters

NameType
optsToolInit

​
Returns

Tool

​
Defined in

src/genai/llm.ts:252

​
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

NameType
contentstring

​
Returns

this

​
Defined in

src/genai/llm.ts:167

​
create

▸ create(opts): LLM

​
Parameters

NameType
optsLLMInit & ChildSpanContext

​
Returns

LLM

​
Defined in

src/genai/llm.ts:124