Co-authored-by: Codex <codex@openai.com>
2.8 KiB
Priorities
The ranked work queue for the autonomous improvement loop. The planner owns this file: each run it turns the roadmap plus an internal scan into a single ordered list — highest-value first — each item linked to a tracking issue. The builder works the top item whose issue is still open. So the planner decides what, the builder builds it.
Bias to capability, not busy-work. The top of this queue is net-new capability from the roadmap's Now/Next items. Hardening/conformance/DX polish is background work (roadmap Ongoing) — kept low here and capped, never allowed to crowd out capability. If an area has had several increments with no user-visible gain, it is done for now; rank real-headroom capability instead.
Reading / editing. An item is done when its linked issue closes (the PR that
builds it adds Closes #<issue>). The human can reorder this list or the issues at
any time — direction always wins.
Off-limits to the loop (planner proposes as notes, never auto-merged queue items): brand/positioning copy, breaking public-API changes, architectural rewrites.
Work queue (ranked)
Capability — the headline (roadmap: Now / Next)
- x402 buyer safety hard stop (#4814) — close the budget-cap bypass and require a real settler for paid configs before autonomous paid-tool use becomes the next thing users copy into real agents.
- Kubernetes operator + CRDs foundation (#4797) — add the first opt-in
Agent,Service, andFlowresource foundation so the services → agents → workflows lifecycle has a native deployment path for Kubernetes users. - A2A external-client conformance (#4815) — make the gateway easier for non-go-micro agents to discover and stream from by serving the well-known agent card path and spec SSE events.
- MCP stdio/ws result conformance (#4813) — return JSON tool results with explicit
isErrorsemantics across transports, backed by a stdio round-trip test.
In flight — do not re-queue
- gRPC-reflection MCP lint follow-up (#4824, PR #4826) — fixes the lint fallout from the merged reflected-gRPC MCP work.
Background — hardening & DX (roadmap: Ongoing; capped)
Background hardening is intentionally empty right now. Recent work covered first-agent
wayfinding, plan/delegate recovery, provider fallback repair, streaming, memory
compaction, retry controls, and provider-failure inspection. Further churn in those
areas should be marked needs-human unless it unlocks a clear user-visible capability.