@overlay/api-client conversation methods when possible.
Typical flow:
- Create or load a conversation with
/api/v1/conversations. - Add user-visible messages with
/api/v1/conversations/message. - Run an Act turn with
/api/v1/conversations/act. - On reconnect, read
/api/v1/conversations/runand reload the authoritative conversation state; AgentRun decides whether a turn is still active. - Stop an active turn with
/api/v1/conversations/stop. - Compare runner behavior with
/api/v1/conversations/run/metrics; the report contains observations and sample counts, not a recommendation.
/api/v1/conversations/act SSE connection while the workflow runs, then persists the final assistant message through the same AgentRun lifecycle.
Runner metrics are available to the authenticated user:
tool_loop and workflow using explicit denominators for latency, provider cost, Workflow observations, disconnect completion, process recovery, tools, cancellation, and stale runs. Work first-token latency is now sampled from the streamed workflow response. Workflow storage bytes are observational rather than invoice-billed bytes.
Conversation messages may contain text, file references, generated UI data, and tool invocation parts. Keep generated and persisted message shapes aligned with @overlay/app-core.
For title generation: