andrewyng--aisuite
Devika
efbbbb91ab
Add an observability layer for agent runs on top of the Agent API. The runner now emits structured trace events for each step (model calls, tool calls, tool-policy denials) and routes them to pluggable sinks, with a trace store and viewer model for inspecting past runs. - aisuite/tracing: trace sinks (in-memory, local JSONL), a JSONL trace store, and a viewer data model for reconstructing runs - aisuite/agents/runner: emit trace events and propagate run context - aisuite/agents/context: ActiveRunContext to correlate nested runs - Runner accepts trace_sinks; RunResult/RunStep carry trace data - tests/agents: trace sink, viewer, trace-output, and tool-policy denial integration coverage Co-authored-by: Rohit <rohit.prasad15@gmail.com>