Generations

A generation is a single LLM call inside a trace. Record it with trace.recordGeneration() / trace.record_generation() after the model call completes.

Record a generation

TypeScript
Python

await lemma.trace({ name: "support-agent", input: userMessage }, async (trace) => {
  const response = await callModel(messages);

  trace.recordGeneration({
    name: "draft-reply",
    input: messages,
    output: response.text,
    model: "gpt-4o",
    llmInputMessages: [{ role: "user", content: userMessage }],
    llmInvocationParameters: { temperature: 0.2 },
  });

  return response.text;
});

def run(trace):
    response = call_model(messages)

    trace.record_generation(
        name="draft-reply",
        input=messages,
        output=response.text,
        model="gpt-4o",
        llm_input_messages=[{"role": "user", "content": user_message}],
        llm_invocation_parameters={"temperature": 0.2},
    )

    return response.text

lemma.trace("support-agent", run, input=user_message)

Measure a live generation

Use startGeneration() / start_generation() when you want a handle before the model call finishes. End it only after the provider returns or fails.

TypeScript
Python

const generation = trace.startGeneration({
  name: "draft-reply",
  input: messages,
  model: "gpt-4o",
});

try {
  const response = await callModel(messages);
  generation.end({
    output: response.text,
    durationMs: response.durationMs,
  });
  return response.text;
} catch (error) {
  generation.end({ error });
  throw error;
}

generation = trace.start_generation(
    name="draft-reply",
    input=messages,
    model="gpt-4o",
)

try:
    response = call_model(messages)
    generation.end(
        output=response.text,
        duration_ms=response.duration_ms,
    )
    return response.text
except Exception as error:
    generation.end(error=error)
    raise

What the SDK records

Field	Attribute keys
Generation kind	Lemma generation marker
Prompt / input	`input.value`
Completion / output	`output.value`
Model	`gen_ai.request.model`, `ai.model.id`
Contract props	Native props such as `llmInputMessages`, `llmInvocationParameters`, and `llmPromptTemplate`; raw `attributes` for escape-hatch keys

See Native contract props for the full list of supported SDK props and the attributes they emit.

Errors

If a model call fails, record a failed generation before rethrowing:

TypeScript
Python

try {
  const response = await callModel(messages);
  trace.recordGeneration({ name: "draft-reply", input: messages, output: response.text });
  return response.text;
} catch (error) {
  trace.recordGeneration({
    name: "draft-reply",
    input: messages,
    status: "ERROR",
    error,
  });
  throw error;
}

try:
    response = call_model(messages)
    trace.record_generation(
        name="draft-reply",
        input=messages,
        output=response.text,
    )
    return response.text
except Exception as error:
    trace.record_generation(
        name="draft-reply",
        input=messages,
        status="ERROR",
        error=error,
    )
    raise

Record a generation

Measure a live generation

What the SDK records

Errors

Next steps

Tool calls

Spans

​Record a generation

​Measure a live generation

​What the SDK records

​Errors

​Next steps

Tool calls

Spans

Record a generation

Measure a live generation

What the SDK records

Errors

Next steps