Observability Should Be a By-product of Inference

Observability plane. Observability should be a by-product of inference

Tracing tools ask your code to carry them: imports, a provider and an exporter, a span around every call, attributes set by hand, trace context passed across every agent boundary, and a flush at the end. The workflow file can double in size, every agent file grows with it, and switching vendors means doing it all again with a different decorator.

The observability plane. In CanyonOS the runtime is the tracer. Every agent-to-agent call is already a message through the runtime and every model call already passes through the gateway next to the agent, so traces, logs, tokens and cost are collected per query and per agent with no instrumentation in your code, and exported as OpenTelemetry to whatever dashboard you already use.

See the observability plane in the product: Observability on canyonos.ai. The same argument, in one page with the other three planes: Why CanyonOS.

• Part 1. Why We Built CanyonOS
• Part 2. Development plane: You should not need a new format for workflows. Python FTW.
• Part 3. Scaling plane: Individual components of a workflow should scale to achieve the desired goals
• Part 4. Observability plane: Observability should be a by-product of inference (this post)
• Part 5. Governance plane: Governance should run concurrently with, and independently of, development