inspect-agent-traces

name	inspect-agent-traces
description	Inspect real agent workflows with the published Traces CLI and export cited local findings.

Inspect agent traces

Use the deterministic CLI first. Keep inspection local and read-only.

Choose the way in

If the trace is already OTLP (a system that emits @tangle-network/agent-trace-contract spans, or any conforming exporter), read it directly. No adapter is involved.

traces validate spans.otlp.jsonl          # what can this trace answer? exit 1 on error findings
traces analyze --otlp spans.otlp.jsonl --out .traces/current.md
traces analyze --otlp results/sessions --out .traces/all.md   # a directory of exports

Use --harness only for coding agents whose on-disk format we do not control. Those adapters are the legacy edge, not the way to integrate a system you own.

A run directory holds the span export beside raw event, stream and SDK logs that are also *.jsonl. Only the OTLP files are read; the rest are listed with what they hold. An otlp/ subdirectory, when present, is read on its own.

Any section headed inputs incomplete, or carrying an Inputs incomplete line above its table, is computed from a field the trace does not carry everywhere. Report those numbers as uncaptured, never as zero spend. The trace conformance section at the top names every such capability once; the markers repeat it where the number actually is.

For a loop trace, read round-over-round convergence (did round N+1 improve on N) and steering chain (which verdict caused which retry) before drawing any conclusion about whether the agent was making progress.

Select the workflow

traces --version
traces list --harness codex --cwd 
traces analyze --harness codex --current --latest-turn --workflow \
  --out .traces/current.md