Batch logging for your agent

Manually log agent traces for frameworks that have already completed the LLM call and need to record it.

For frameworks that have already completed the LLM call and only need to record it, use weave.log_turn and weave.log_conversation. All spans are created and ended immediately without keeping any context managers open.

Data logged this way can be historical. No live conversation is needed. Set conversation_id to any stable string that uniquely identifies the conversation. Turns that share the same conversation_id are grouped as a single conversation in the Agents view.

If you’re building your own agent loop, use the real-time instrumentation APIs described in Trace your agents instead.

Log a turn

To record a single completed turn after it happens, use weave.log_turn. It accepts a fully-formed turn, including all LLM and tool spans.

Python

weave.init("[YOUR-TEAM]/[YOUR-PROJECT]")

from weave.conversation import LLM, Message, Tool, Usage

llm_span = LLM(
    model="gpt-4o",
    provider_name="openai",
    input_messages=[Message(role="user", content="What is the weather?")],
    output_messages=[Message(role="assistant", content="Let me check.")],
    usage=Usage(input_tokens=100, output_tokens=20),
)

tool_span = Tool(
    name="get_weather",
    arguments='{"city": "Tokyo"}',
    result='"24°C, sunny"',
)

llm_span2 = LLM(
    model="gpt-4o",
    provider_name="openai",
    input_messages=[Message(role="user", content="What is the weather?")],
    output_messages=[Message(role="assistant", content="It is 24°C and sunny.")],
    usage=Usage(input_tokens=150, output_tokens=30),
)

# Log a turn with all its spans.
weave.log_turn(
    conversation_id="my-conversation-abc",
    agent_name="weather-bot",
    messages=[
        Message(role="user", content="What is the weather in Tokyo?"),
        Message(role="assistant", content="It is 24°C and sunny in Tokyo."),
    ],
    spans=[llm_span, tool_span, llm_span2],
)

TypeScript

This feature is not available in the TypeScript SDK yet.

log_turn returns a LogResult containing the trace IDs of the emitted spans.

An optional model parameter on log_turn sets the model on the turn’s own span, not on the child LLM spans. Each LLM span carries its own model independently. If a turn uses multiple models, set model on log_turn to whichever you consider the primary model for that turn.

Log a conversation

To bulk-import a complete, multi-turn conversation at once, use weave.log_conversation. The turns parameter accepts a list of Turn objects, each constructed the same way as the previous log_turn example.

Python

weave.log_conversation(
    conversation_id="my-conversation-abc",
    agent_name="weather-bot",
    turns=[turn_1, turn_2],
)

TypeScript

This feature is not available in the TypeScript SDK yet.