Batch logging for your agent

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

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

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

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

weave.log_turn

weave.log_turn accepts a fully-formed turn, including all LLM and tool spans.

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

from weave.session.session 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(
    session_id="my-session-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],
)

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.

weave.log_session

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

weave.log_session(
    session_id="my-session-abc",
    agent_name="weather-bot",
    turns=[turn_1, turn_2],
)