displacement: align span emission to OpenInference semantic conventions #66
Labels
No labels
burndown-2026-06
coherence-core
consult
headless
interactive
P0
P1
P2
P3
P4
No milestone
No project
No assignees
1 participant
Due date
No due date set.
Dependencies
No dependencies set.
Reference
coilyco-flight-deck/otel-a2a-relay#66
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Displacement: align span emission to OpenInference semantic conventions
From the 2026-06-17 displacement scout.
The relay's span-EMISSION layer overlaps OSS agent-observability instrumentation:
OpenInference- OTel-aligned semantic conventions + drop-in instrumentation, 10 span kinds (CHAIN, LLM, TOOL, RETRIEVER, EMBEDDING, AGENT, RERANKER, GUARDRAIL, EVALUATOR, PROMPT). Arize-maintained - and the Phoenix/Arize MCP is already in Kai's inventory.OpenLLMetry- Traceloop; mid-donation to the OTel project (would become the de-facto official GenAI instrumentation if accepted).Action (design call)
Keep custom
The a2a-relay PROTOCOL - envelope verification, agent channel, the o2r request/verify handshake - is genuinely novel and has no OSS equivalent.
Caution
Convention alignment is low-risk; if pulling in an OpenInference package as a dependency, run
tooling-supply-chain-audit+ pin first.Closing. o2r is archived in the June 2026 surface reduction - an optional agent channel, unused autonomously. Handover doctrine moves to human-mediated.