Access these through the tracing module:
start_conversation
Create and activate a conversation. Sets the contextvar for cross-module access.
attributes are stamped on every span this conversation emits (for example an
integration identity like weave.integration.*). Use custom,
non-semconv keys: set semantic-convention fields via the typed params
(conversation_name, model, …). A key that collides with a span’s
own gen_ai.* / weave.* attribute is unsupported; which value
wins is path-dependent (streaming vs log_turn).
start_turn
Create and activate a turn. Uses the current conversation if available.
Starts the span and makes it current. Without a conversation, the turn
has no conversation id. Finish with end_turn(), end(), or with.
start_llm
Create and activate an LLM call. Uses the current turn if available.
Starts the span and makes it current, even without an active turn.
Pass provider_name explicitly. The SDK does not infer it from the
model identifier: prefix-based guessing misattributes user fine-tunes
(for example a model named text-...) and bakes assumptions about future
model names into telemetry that’s expensive to correct after the fact.
Create and start a tool execution span.
The Tool’s OTel span automatically becomes a child of whatever span is
current in OTel context; typically a Turn span if one is active. No
explicit turn delegation is needed: parent-child propagation happens
via OTel context, not via the Conversation SDK contextvars.
start_subagent
Create and start a sub-agent invocation span.
The SubAgent’s OTel span automatically becomes a child of whatever span
is current in OTel context; typically a Turn span if one is active.
Mirrors start_tool in shape; OTel context handles parent-child
propagation, no explicit delegation is needed.
end_conversation
End the current conversation (from contextvar).
end_turn
End the current turn (from contextvar).
end_llm
End the current LLM call (from contextvar).
get_current_conversation
Return the active conversation from contextvar, or None.
get_current_turn
Return the active turn from contextvar, or None.
get_current_llm
Return the active LLM call from contextvar, or None. Last modified on September 30, 2026
